Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.5290. Min Act: -0.1700
Data Index: 5619361 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.5290. Min Act: -0.1700
Data Index: 3814326 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.5290. Min Act: -0.1700
Data Index: 693852 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 6087145 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 7055483 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 8252182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 2221565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 8649832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 2293475 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 3238775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 10366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4976. Min Act: -0.1700
Data Index: 3093946 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 1204399 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 5171322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 531344 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 5138492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 2682077 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 4339659 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 2593885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5290. Min Range: -3.5290
Max Act: 3.4663. Min Act: -0.1700
Data Index: 2335809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19