Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.2523. Min Act: -0.1700
Data Index: 7952408 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.2523. Min Act: -0.1700
Data Index: 14261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.2523. Min Act: -0.1700
Data Index: 4680748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1898. Min Act: -0.1700
Data Index: 3417540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1586. Min Act: -0.1700
Data Index: 3909033 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 7325792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1586. Min Act: -0.1700
Data Index: 6866844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 1478354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 6158866 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 4909299 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 4909313 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 8462406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 4909333 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.1273. Min Act: -0.1700
Data Index: 943785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0960. Min Act: -0.1700
Data Index: 5486872 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0960. Min Act: -0.1700
Data Index: 2638582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0960. Min Act: -0.1700
Data Index: 4512412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0960. Min Act: -0.1700
Data Index: 7072630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0960. Min Act: -0.1700
Data Index: 4909317 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2523. Min Range: -4.2523
Max Act: 4.0648. Min Act: -0.1700
Data Index: 2737822 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19