Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.4315. Min Act: -0.1700
Data Index: 6152706 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.3690. Min Act: -0.1700
Data Index: 6192843 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.1815. Min Act: -0.1700
Data Index: 8148856 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.1815. Min Act: -0.1700
Data Index: 580353 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.1502. Min Act: -0.1700
Data Index: 2919704 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0877. Min Act: -0.1700
Data Index: 5764813 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.1502. Min Act: -0.1700
Data Index: 6583848 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.1190. Min Act: -0.1700
Data Index: 4977324 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0565. Min Act: -0.1700
Data Index: 5518821 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0565. Min Act: -0.1700
Data Index: 2347247 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0565. Min Act: -0.1700
Data Index: 6221047 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0565. Min Act: -0.1700
Data Index: 1879442 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0565. Min Act: -0.1700
Data Index: 6486211 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0252. Min Act: -0.1700
Data Index: 8788328 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4315. Min Range: -4.4315
Max Act: 4.0252. Min Act: -0.1700
Data Index: 4903775 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4315. Min Range: -4.4315
Max Act: 3.9939. Min Act: -0.1700
Data Index: 2741827 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4315. Min Range: -4.4315
Max Act: 3.9627. Min Act: -0.1700
Data Index: 5331931 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4315. Min Range: -4.4315
Max Act: 3.9939. Min Act: -0.1700
Data Index: 1344493 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4315. Min Range: -4.4315
Max Act: 3.9939. Min Act: -0.1700
Data Index: 7452625 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4315. Min Range: -4.4315
Max Act: 3.9939. Min Act: -0.1700
Data Index: 27290 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19