Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4407 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.9229. Min Range: -15.9229
Max Act: 15.9229. Min Act: -0.1700
Data Index: 2314306 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.9229. Min Act: -0.1700
Data Index: 7464129 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.7979. Min Act: -0.1700
Data Index: 8556548 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.7354. Min Act: -0.1700
Data Index: 7897105 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.7354. Min Act: -0.1700
Data Index: 5070364 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.6729. Min Act: -0.1700
Data Index: 2920064 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.5479. Min Act: -0.1700
Data Index: 5947644 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.6729. Min Act: -0.1700
Data Index: 4939486 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.6729. Min Act: -0.1700
Data Index: 5123966 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.5479. Min Act: -0.1700
Data Index: 2424669 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.5479. Min Act: -0.1700
Data Index: 151351 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.5479. Min Act: -0.1700
Data Index: 711412 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.5479. Min Act: -0.1700
Data Index: 3428371 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.4229. Min Act: -0.1700
Data Index: 848290 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.4229. Min Act: -0.1700
Data Index: 2057883 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.4229. Min Act: -0.1700
Data Index: 3892263 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.3604. Min Act: -0.1700
Data Index: 3399303 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.2979. Min Act: -0.1700
Data Index: 7370449 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.2979. Min Act: -0.1700
Data Index: 2855516 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.9229. Min Range: -15.9229
Max Act: 14.2979. Min Act: -0.1700
Data Index: 3455304 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19