Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5948 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.6629. Min Act: -0.1700
Data Index: 7674123 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.6004. Min Act: -0.1700
Data Index: 4656565 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.5379. Min Act: -0.1700
Data Index: 5793491 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.4754. Min Act: -0.1700
Data Index: 8813341 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.2879. Min Act: -0.1700
Data Index: 158582 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.2566. Min Act: -0.1700
Data Index: 7939020 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.2254. Min Act: -0.1700
Data Index: 2391784 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.2254. Min Act: -0.1700
Data Index: 1365505 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.1316. Min Act: -0.1700
Data Index: 2512066 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.1004. Min Act: -0.1700
Data Index: 4628670 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.0379. Min Act: -0.1700
Data Index: 5337379 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6629. Min Range: -8.6629
Max Act: 8.0379. Min Act: -0.1700
Data Index: 1761413 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.9129. Min Act: -0.1700
Data Index: 8270658 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.7879. Min Act: -0.1700
Data Index: 4352468 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.8191. Min Act: -0.1700
Data Index: 1350537 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.7879. Min Act: -0.1700
Data Index: 5744658 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.7566. Min Act: -0.1700
Data Index: 8238420 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.7566. Min Act: -0.1700
Data Index: 8690976 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.7566. Min Act: -0.1700
Data Index: 3314561 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6629. Min Range: -8.6629
Max Act: 7.7566. Min Act: -0.1700
Data Index: 3337056 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19