Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.8113. Min Act: -0.1700
Data Index: 6049251 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7795. Min Act: -0.1700
Data Index: 6716988 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7795. Min Act: -0.1700
Data Index: 1384969 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7635. Min Act: -0.1700
Data Index: 2655875 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7476. Min Act: -0.1700
Data Index: 431464 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7476. Min Act: -0.1700
Data Index: 3003824 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7316. Min Act: -0.1700
Data Index: 4461488 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7156. Min Act: -0.1700
Data Index: 5667526 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7156. Min Act: -0.1700
Data Index: 2871788 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.7156. Min Act: -0.1700
Data Index: 3880985 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6996. Min Act: -0.1700
Data Index: 1307164 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6996. Min Act: -0.1700
Data Index: 6874890 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6676. Min Act: -0.1700
Data Index: 3750259 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6515. Min Act: -0.1700
Data Index: 1588779 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6515. Min Act: -0.1700
Data Index: 8445019 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6515. Min Act: -0.1700
Data Index: 6372542 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6194. Min Act: -0.1700
Data Index: 8826873 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6355. Min Act: -0.1700
Data Index: 7008870 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.5872. Min Act: -0.1700
Data Index: 4076536 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8113. Min Range: -2.8113
Max Act: 2.6033. Min Act: -0.1700
Data Index: 6195693 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19