Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.5630. Min Act: -0.1700
Data Index: 6388321 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.4068. Min Act: -0.1700
Data Index: 3143721 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2818. Min Act: -0.1700
Data Index: 3587789 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2818. Min Act: -0.1700
Data Index: 4482763 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2505. Min Act: -0.1700
Data Index: 3202037 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.2505. Min Act: -0.1700
Data Index: 6342267 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1568. Min Act: -0.1700
Data Index: 2397054 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1568. Min Act: -0.1700
Data Index: 6416390 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1568. Min Act: -0.1700
Data Index: 7780760 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1568. Min Act: -0.1700
Data Index: 1163438 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.1255. Min Act: -0.1700
Data Index: 1685505 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.0943. Min Act: -0.1700
Data Index: 1554101 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.0943. Min Act: -0.1700
Data Index: 6411472 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.0943. Min Act: -0.1700
Data Index: 4827858 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.0630. Min Act: -0.1700
Data Index: 5738048 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.0318. Min Act: -0.1700
Data Index: 4091729 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.0318. Min Act: -0.1700
Data Index: 4806650 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5630. Min Range: -6.5630
Max Act: 6.0318. Min Act: -0.1700
Data Index: 418031 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5630. Min Range: -6.5630
Max Act: 5.9693. Min Act: -0.1700
Data Index: 790390 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5630. Min Range: -6.5630
Max Act: 5.9693. Min Act: -0.1700
Data Index: 4622943 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19