Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5982. Min Act: -0.1700
Data Index: 4728442 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5670. Min Act: -0.1700
Data Index: 5462748 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5670. Min Act: -0.1700
Data Index: 5730132 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5357. Min Act: -0.1700
Data Index: 7364716 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5357. Min Act: -0.1700
Data Index: 1522121 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.5045. Min Act: -0.1700
Data Index: 112247 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3795. Min Act: -0.1700
Data Index: 8715709 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3795. Min Act: -0.1700
Data Index: 4831059 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.4107. Min Act: -0.1700
Data Index: 5543951 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.3170. Min Act: -0.1700
Data Index: 7272453 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3073777 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.1607. Min Act: -0.1700
Data Index: 6277690 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.1295. Min Act: -0.1700
Data Index: 917520 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.1920. Min Act: -0.1700
Data Index: 4661502 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.0670. Min Act: -0.1700
Data Index: 7855965 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.0670. Min Act: -0.1700
Data Index: 1944960 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.0982. Min Act: -0.1700
Data Index: 5100928 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.0670. Min Act: -0.1700
Data Index: 2570228 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.0670. Min Act: -0.1700
Data Index: 4670343 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5982. Min Range: -6.5982
Max Act: 6.0357. Min Act: -0.1700
Data Index: 190800 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19