Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 357 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.5445. Min Act: -0.1700
Data Index: 4066091 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.4147. Min Act: -0.1700
Data Index: 5653025 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3984. Min Act: -0.1700
Data Index: 4066087 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3657. Min Act: -0.1700
Data Index: 2006231 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3657. Min Act: -0.1699
Data Index: 2915070 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3494. Min Act: -0.1700
Data Index: 4066088 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3494. Min Act: -0.1700
Data Index: 4066060 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3165. Min Act: -0.1700
Data Index: 7300335 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3165. Min Act: -0.1700
Data Index: 6275702 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3165. Min Act: -0.1700
Data Index: 4362648 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 6275698 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 3246972 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 4066083 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 3062853 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 4729756 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 3771262 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 356756 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 4066085 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.2672. Min Act: -0.1700
Data Index: 6275697 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5445. Min Range: -2.5445
Max Act: 2.3001. Min Act: -0.1700
Data Index: 6275701 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19