Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0853. Min Range: -7.0853
Max Act: 7.0853. Min Act: -0.1700
Data Index: 5462611 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0853. Min Range: -7.0853
Max Act: 7.0541. Min Act: -0.1700
Data Index: 5747535 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0853. Min Range: -7.0853
Max Act: 7.0228. Min Act: -0.1700
Data Index: 4966597 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.9916. Min Act: -0.1700
Data Index: 2294293 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.8666. Min Act: -0.1700
Data Index: 7659765 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.8041. Min Act: -0.1700
Data Index: 4667748 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.8353. Min Act: -0.1700
Data Index: 755090 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.8353. Min Act: -0.1700
Data Index: 7767757 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.8041. Min Act: -0.1700
Data Index: 5098987 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7416. Min Act: -0.1700
Data Index: 6166791 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7103. Min Act: -0.1700
Data Index: 6468811 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7103. Min Act: -0.1700
Data Index: 4422763 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7103. Min Act: -0.1700
Data Index: 6797104 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.7103. Min Act: -0.1700
Data Index: 8243111 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 5575453 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 6547834 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 971251 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 749644 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6478. Min Act: -0.1700
Data Index: 255920 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0853. Min Range: -7.0853
Max Act: 6.6166. Min Act: -0.1700
Data Index: 6742192 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19