Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.3353. Min Act: -0.1700
Data Index: 2806929 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3353. Min Range: -6.3353
Max Act: 6.1791. Min Act: -0.1700
Data Index: 4295554 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.9916. Min Act: -0.1700
Data Index: 4407924 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.9916. Min Act: -0.1700
Data Index: 8249999 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.9291. Min Act: -0.1700
Data Index: 8270965 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8978. Min Act: -0.1700
Data Index: 3164051 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8353. Min Act: -0.1700
Data Index: 5641065 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8666. Min Act: -0.1700
Data Index: 6835441 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8666. Min Act: -0.1700
Data Index: 4510802 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8041. Min Act: -0.1700
Data Index: 5055155 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.7728. Min Act: -0.1700
Data Index: 6359333 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8353. Min Act: -0.1700
Data Index: 2681442 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8041. Min Act: -0.1700
Data Index: 4510801 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.7728. Min Act: -0.1700
Data Index: 4615905 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.7728. Min Act: -0.1700
Data Index: 6887668 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.7728. Min Act: -0.1700
Data Index: 8165804 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.8041. Min Act: -0.1700
Data Index: 8334978 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.7103. Min Act: -0.1700
Data Index: 5055153 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.6478. Min Act: -0.1700
Data Index: 4427786 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3353. Min Range: -6.3353
Max Act: 5.6478. Min Act: -0.1700
Data Index: 590392 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19