Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4170 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.9379. Min Act: -0.1700
Data Index: 7828261 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6879. Min Act: -0.1700
Data Index: 1191037 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.7504. Min Act: -0.1700
Data Index: 6965781 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6566. Min Act: -0.1700
Data Index: 4182121 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6254. Min Act: -0.1700
Data Index: 3935886 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.6254. Min Act: -0.1700
Data Index: 169399 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5941. Min Act: -0.1700
Data Index: 2534804 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5316. Min Act: -0.1700
Data Index: 262073 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5316. Min Act: -0.1700
Data Index: 5422199 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 6724946 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 807142 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.4691. Min Act: -0.1700
Data Index: 7533071 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 8391952 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.5004. Min Act: -0.1700
Data Index: 2295695 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.4691. Min Act: -0.1700
Data Index: 8790823 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.4691. Min Act: -0.1700
Data Index: 1774041 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.4691. Min Act: -0.1700
Data Index: 846274 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.4379. Min Act: -0.1700
Data Index: 1488901 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.4066. Min Act: -0.1700
Data Index: 3203607 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9379. Min Range: -6.9379
Max Act: 6.4379. Min Act: -0.1700
Data Index: 8240617 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19