Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 97 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2587. Min Range: -6.2587
Max Act: 6.2587. Min Act: -0.1700
Data Index: 4085321 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2587. Min Range: -6.2587
Max Act: 6.0400. Min Act: -0.1700
Data Index: 5645791 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2587. Min Range: -6.2587
Max Act: 6.0087. Min Act: -0.1700
Data Index: 1944886 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9775. Min Act: -0.1700
Data Index: 4734177 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2587. Min Range: -6.2587
Max Act: 6.0087. Min Act: -0.1700
Data Index: 3313484 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9462. Min Act: -0.1700
Data Index: 8417236 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9462. Min Act: -0.1700
Data Index: 6020435 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9462. Min Act: -0.1700
Data Index: 7162656 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9150. Min Act: -0.1700
Data Index: 8342367 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9150. Min Act: -0.1700
Data Index: 2139225 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9462. Min Act: -0.1700
Data Index: 8466555 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9150. Min Act: -0.1700
Data Index: 7084355 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.9150. Min Act: -0.1700
Data Index: 8457139 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.8837. Min Act: -0.1700
Data Index: 7735464 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.8837. Min Act: -0.1700
Data Index: 7711333 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.8837. Min Act: -0.1700
Data Index: 7076427 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.8837. Min Act: -0.1700
Data Index: 58760 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.8837. Min Act: -0.1700
Data Index: 2072311 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.8837. Min Act: -0.1700
Data Index: 8102162 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2587. Min Range: -6.2587
Max Act: 5.8837. Min Act: -0.1700
Data Index: 7695784 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19