Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2496 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.1032. Min Act: -0.1700
Data Index: 1735895 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.1345. Min Act: -0.1700
Data Index: 1200583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.1345. Min Act: -0.1700
Data Index: 1530247 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.1345. Min Act: -0.1700
Data Index: 4446649 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0719. Min Act: -0.1700
Data Index: 6118752 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0719. Min Act: -0.1700
Data Index: 4393431 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0719. Min Act: -0.1700
Data Index: 4441910 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.1032. Min Act: -0.1700
Data Index: 2586168 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0719. Min Act: -0.1700
Data Index: 3554836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0719. Min Act: -0.1700
Data Index: 565769 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0407. Min Act: -0.1700
Data Index: 7854330 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0407. Min Act: -0.1700
Data Index: 8775785 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0407. Min Act: -0.1700
Data Index: 8014016 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0407. Min Act: -0.1700
Data Index: 486610 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0094. Min Act: -0.1700
Data Index: 1873094 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0407. Min Act: -0.1700
Data Index: 8535347 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0094. Min Act: -0.1700
Data Index: 72417 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0719. Min Act: -0.1700
Data Index: 4026517 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0094. Min Act: -0.1700
Data Index: 2613208 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1345. Min Range: -4.1345
Max Act: 4.0094. Min Act: -0.1700
Data Index: 5530781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19