Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5362 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.8341. Min Act: -0.1700
Data Index: 3553567 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.7716. Min Act: -0.1700
Data Index: 1599539 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.7716. Min Act: -0.1700
Data Index: 980631 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.7091. Min Act: -0.1700
Data Index: 8163945 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 988706 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 7451198 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 8411922 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 8448366 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 1469236 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 1115058 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6466. Min Act: -0.1700
Data Index: 2617338 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6466. Min Act: -0.1700
Data Index: 7413897 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 1566040 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6466. Min Act: -0.1700
Data Index: 4840503 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6466. Min Act: -0.1700
Data Index: 8294210 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6779. Min Act: -0.1700
Data Index: 2309600 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6154. Min Act: -0.1700
Data Index: 6154631 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6154. Min Act: -0.1700
Data Index: 2030372 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6466. Min Act: -0.1700
Data Index: 572435 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8341. Min Range: -5.8341
Max Act: 5.6154. Min Act: -0.1700
Data Index: 5753684 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19