Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5939 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.2117. Min Act: -0.1700
Data Index: 2666481 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0542. Min Act: -0.1700
Data Index: 2443448 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0226. Min Act: -0.1700
Data Index: 4281877 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0226. Min Act: -0.1700
Data Index: 284930 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0226. Min Act: -0.1700
Data Index: 4128607 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0226. Min Act: -0.1700
Data Index: 5658261 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0226. Min Act: -0.1700
Data Index: 7593223 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0068. Min Act: -0.1700
Data Index: 3121951 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0068. Min Act: -0.1700
Data Index: 1950519 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9910. Min Act: -0.1700
Data Index: 5787681 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9910. Min Act: -0.1700
Data Index: 3986553 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2117. Min Range: -3.2117
Max Act: 3.0068. Min Act: -0.1700
Data Index: 4910475 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9752. Min Act: -0.1700
Data Index: 1431140 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9910. Min Act: -0.1700
Data Index: 322197 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9594. Min Act: -0.1700
Data Index: 920541 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9435. Min Act: -0.1700
Data Index: 5570799 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9594. Min Act: -0.1700
Data Index: 3989175 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9594. Min Act: -0.1700
Data Index: 6028995 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9594. Min Act: -0.1700
Data Index: 7516846 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2117. Min Range: -3.2117
Max Act: 2.9435. Min Act: -0.1700
Data Index: 2142257 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19