Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.4484. Min Act: -0.1700
Data Index: 6965634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.4484. Min Act: -0.1700
Data Index: 3583870 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3857. Min Act: -0.1700
Data Index: 959612 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 146020 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 6867151 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 4278394 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 6473100 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 2571710 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 4166810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 6426226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 1797991 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 6317987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 5193510 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 5736463 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 1734794 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 567526 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 533463 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 5415709 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 3532748 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4484. Min Range: -3.4484
Max Act: 3.3543. Min Act: -0.1700
Data Index: 2167522 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19