Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.3747. Min Act: -0.1700
Data Index: 1884619 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.4059. Min Act: -0.1700
Data Index: 772595 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.3747. Min Act: -0.1700
Data Index: 7288012 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.4059. Min Act: -0.1700
Data Index: 7910749 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.3122. Min Act: -0.1700
Data Index: 5402922 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.3122. Min Act: -0.1700
Data Index: 55529 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.2184. Min Act: -0.1700
Data Index: 5571565 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.2184. Min Act: -0.1700
Data Index: 4827642 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.0934. Min Act: -0.1700
Data Index: 2026828 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.0934. Min Act: -0.1700
Data Index: 8812246 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.0309. Min Act: -0.1700
Data Index: 5895964 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9997. Min Act: -0.1700
Data Index: 5525424 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4059. Min Range: -6.4059
Max Act: 6.0309. Min Act: -0.1700
Data Index: 569997 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9372. Min Act: -0.1700
Data Index: 338809 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9997. Min Act: -0.1700
Data Index: 1589386 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9684. Min Act: -0.1700
Data Index: 6595167 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9059. Min Act: -0.1700
Data Index: 8516077 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9684. Min Act: -0.1700
Data Index: 2556393 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9372. Min Act: -0.1700
Data Index: 4574389 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4059. Min Range: -6.4059
Max Act: 5.9372. Min Act: -0.1700
Data Index: 5980031 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19