Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1496 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.4029. Min Act: -0.1700
Data Index: 1933952 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.3716. Min Act: -0.1700
Data Index: 3165902 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.2779. Min Act: -0.1700
Data Index: 3243700 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.3091. Min Act: -0.1700
Data Index: 2762955 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.2154. Min Act: -0.1700
Data Index: 1946324 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.1529. Min Act: -0.1700
Data Index: 5581232 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.2154. Min Act: -0.1700
Data Index: 5128092 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.1841. Min Act: -0.1700
Data Index: 4126548 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.1216. Min Act: -0.1700
Data Index: 1817925 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.1216. Min Act: -0.1700
Data Index: 5358555 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4029. Min Range: -6.4029
Max Act: 6.0591. Min Act: -0.1700
Data Index: 3631775 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9654. Min Act: -0.1700
Data Index: 1767870 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9966. Min Act: -0.1700
Data Index: 6731917 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9341. Min Act: -0.1700
Data Index: 4039708 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9654. Min Act: -0.1700
Data Index: 1964373 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9029. Min Act: -0.1700
Data Index: 603411 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9029. Min Act: -0.1700
Data Index: 1641174 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.8404. Min Act: -0.1700
Data Index: 1152323 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.9029. Min Act: -0.1700
Data Index: 4798885 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4029. Min Range: -6.4029
Max Act: 5.8716. Min Act: -0.1700
Data Index: 3188196 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19