Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.5448. Min Act: -0.1700
Data Index: 3389856 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.5135. Min Act: -0.1700
Data Index: 2678935 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4823. Min Act: -0.1700
Data Index: 678382 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4823. Min Act: -0.1700
Data Index: 2148495 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4510. Min Act: -0.1700
Data Index: 7792698 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4510. Min Act: -0.1700
Data Index: 7968100 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4198. Min Act: -0.1700
Data Index: 8437440 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4198. Min Act: -0.1700
Data Index: 829387 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4198. Min Act: -0.1700
Data Index: 6768286 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4198. Min Act: -0.1700
Data Index: 1628143 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3885. Min Act: -0.1700
Data Index: 4738256 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3885. Min Act: -0.1700
Data Index: 4090485 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3885. Min Act: -0.1700
Data Index: 1425045 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3573. Min Act: -0.1700
Data Index: 8756159 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3573. Min Act: -0.1700
Data Index: 7833399 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3260. Min Act: -0.1700
Data Index: 70898 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3260. Min Act: -0.1700
Data Index: 6418509 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3260. Min Act: -0.1700
Data Index: 1425044 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3260. Min Act: -0.1700
Data Index: 2622043 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3260. Min Act: -0.1700
Data Index: 5338307 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19