Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 154 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.4191. Min Range: -11.4191
Max Act: 11.4191. Min Act: -0.1700
Data Index: 3010127 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.9816. Min Act: -0.1700
Data Index: 1860954 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.7941. Min Act: -0.1700
Data Index: 4045624 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.6691. Min Act: -0.1700
Data Index: 6127581 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.6691. Min Act: -0.1700
Data Index: 7550496 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.6691. Min Act: -0.1700
Data Index: 6127572 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.6066. Min Act: -0.1700
Data Index: 194191 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.6066. Min Act: -0.1700
Data Index: 3060875 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.5441. Min Act: -0.1700
Data Index: 6880456 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 2975505 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 3017216 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 2501227 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 4418520 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4816. Min Act: -0.1700
Data Index: 8083128 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.3566. Min Act: -0.1700
Data Index: 984472 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 5561981 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 326645 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 5830924 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.4191. Min Act: -0.1700
Data Index: 684877 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4191. Min Range: -11.4191
Max Act: 10.3566. Min Act: -0.1700
Data Index: 511798 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19