Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.4940. Min Act: -0.1700
Data Index: 832010 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.4940. Min Act: -0.1700
Data Index: 6936032 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.4315. Min Act: -0.1700
Data Index: 8082277 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.3690. Min Act: -0.1700
Data Index: 5295984 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.3690. Min Act: -0.1700
Data Index: 4903988 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.3065. Min Act: -0.1700
Data Index: 6038405 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.2440. Min Act: -0.1700
Data Index: 7691583 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1815. Min Act: -0.1700
Data Index: 2738275 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1815. Min Act: -0.1700
Data Index: 2382806 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1815. Min Act: -0.1700
Data Index: 6424182 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1815. Min Act: -0.1700
Data Index: 6510534 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1190. Min Act: -0.1700
Data Index: 5650136 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1190. Min Act: -0.1700
Data Index: 8079409 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1190. Min Act: -0.1700
Data Index: 257072 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.1190. Min Act: -0.1700
Data Index: 8449832 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.0565. Min Act: -0.1700
Data Index: 7799689 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.0565. Min Act: -0.1700
Data Index: 1863942 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.0565. Min Act: -0.1700
Data Index: 8286369 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4940. Min Range: -8.4940
Max Act: 8.0565. Min Act: -0.1700
Data Index: 480789 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4940. Min Range: -8.4940
Max Act: 7.9940. Min Act: -0.1700
Data Index: 1386003 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19