Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4930. Min Act: -0.1700
Data Index: 6690976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 5974309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 8587043 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 5076135 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 2311523 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 7656896 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 4404012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 4560399 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 2662873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4616. Min Act: -0.1700
Data Index: 8356298 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4303. Min Act: -0.1700
Data Index: 7806234 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4303. Min Act: -0.1700
Data Index: 2682884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4303. Min Act: -0.1700
Data Index: 3664527 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.4303. Min Act: -0.1700
Data Index: 3944515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.3362. Min Act: -0.1700
Data Index: 2026710 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.3362. Min Act: -0.1700
Data Index: 2799045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.3362. Min Act: -0.1700
Data Index: 6625521 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.2734. Min Act: -0.1700
Data Index: 5084582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.3048. Min Act: -0.1700
Data Index: 5575613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4930. Min Range: -3.4930
Max Act: 3.3048. Min Act: -0.1700
Data Index: 1827885 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19