Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.7340. Min Act: -0.1700
Data Index: 4819876 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.7340. Min Act: -0.1700
Data Index: 5426653 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.7027. Min Act: -0.1700
Data Index: 6188512 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.7027. Min Act: -0.1700
Data Index: 3472873 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.6402. Min Act: -0.1700
Data Index: 3590567 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.6402. Min Act: -0.1700
Data Index: 269577 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.6090. Min Act: -0.1700
Data Index: 6269806 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.6090. Min Act: -0.1700
Data Index: 4459501 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.6090. Min Act: -0.1700
Data Index: 7974117 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.6090. Min Act: -0.1700
Data Index: 5146734 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.6090. Min Act: -0.1700
Data Index: 7160285 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5777. Min Act: -0.1700
Data Index: 5265707 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5777. Min Act: -0.1700
Data Index: 2326807 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5777. Min Act: -0.1700
Data Index: 224985 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5777. Min Act: -0.1700
Data Index: 8317184 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5777. Min Act: -0.1700
Data Index: 4183265 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5465. Min Act: -0.1700
Data Index: 4950514 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5152. Min Act: -0.1700
Data Index: 3773113 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5152. Min Act: -0.1700
Data Index: 7339394 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7340. Min Range: -6.7340
Max Act: 6.5152. Min Act: -0.1700
Data Index: 1089920 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19