Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.7350. Min Act: -0.1700
Data Index: 2770089 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.7038. Min Act: -0.1700
Data Index: 1780979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6725. Min Act: -0.1700
Data Index: 2605793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6725. Min Act: -0.1700
Data Index: 6397513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 539361 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6725. Min Act: -0.1700
Data Index: 7427868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 7156440 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 2116041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 7464416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 137320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 5092008 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 6560538 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 525976 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 3583902 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6412. Min Act: -0.1700
Data Index: 7537389 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6099. Min Act: -0.1700
Data Index: 3941410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6099. Min Act: -0.1700
Data Index: 1246896 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6099. Min Act: -0.1700
Data Index: 2506703 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6099. Min Act: -0.1700
Data Index: 5242246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7350. Min Range: -3.7350
Max Act: 3.6099. Min Act: -0.1700
Data Index: 4933351 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19