Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3198. Min Range: -6.3198
Max Act: 6.3198. Min Act: -0.1700
Data Index: 3077462 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3198. Min Range: -6.3198
Max Act: 6.1010. Min Act: -0.1700
Data Index: 1824032 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3198. Min Range: -6.3198
Max Act: 6.0073. Min Act: -0.1700
Data Index: 447204 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.9448. Min Act: -0.1700
Data Index: 7174056 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.8823. Min Act: -0.1700
Data Index: 3236523 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.8198. Min Act: -0.1700
Data Index: 4628744 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.8198. Min Act: -0.1700
Data Index: 4815447 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.7573. Min Act: -0.1700
Data Index: 1910911 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.7260. Min Act: -0.1700
Data Index: 2219755 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6948. Min Act: -0.1700
Data Index: 1493648 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6635. Min Act: -0.1700
Data Index: 2821608 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6323. Min Act: -0.1700
Data Index: 3190741 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6635. Min Act: -0.1700
Data Index: 7116650 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6635. Min Act: -0.1700
Data Index: 3090762 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6635. Min Act: -0.1700
Data Index: 3512744 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6010. Min Act: -0.1700
Data Index: 3188877 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6323. Min Act: -0.1700
Data Index: 456269 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6635. Min Act: -0.1700
Data Index: 3243354 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6010. Min Act: -0.1700
Data Index: 862571 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3198. Min Range: -6.3198
Max Act: 5.6010. Min Act: -0.1700
Data Index: 2404000 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19