Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1823 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8980. Min Act: -0.1700
Data Index: 8474411 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8667. Min Act: -0.1700
Data Index: 4233501 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8354. Min Act: -0.1700
Data Index: 588550 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8667. Min Act: -0.1700
Data Index: 6285727 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8667. Min Act: -0.1700
Data Index: 3223992 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8354. Min Act: -0.1700
Data Index: 5331477 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8042. Min Act: -0.1700
Data Index: 7262761 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8354. Min Act: -0.1700
Data Index: 5544424 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.8042. Min Act: -0.1700
Data Index: 7363974 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7885. Min Act: -0.1700
Data Index: 1379922 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7729. Min Act: -0.1700
Data Index: 2585298 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7885. Min Act: -0.1700
Data Index: 5725561 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7260. Min Act: -0.1700
Data Index: 4890893 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7416. Min Act: -0.1700
Data Index: 4226257 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7260. Min Act: -0.1700
Data Index: 1996054 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7103. Min Act: -0.1700
Data Index: 2187058 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7103. Min Act: -0.1700
Data Index: 337716 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7103. Min Act: -0.1700
Data Index: 6754449 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7260. Min Act: -0.1700
Data Index: 4198076 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8980. Min Range: -3.8980
Max Act: 3.7103. Min Act: -0.1700
Data Index: 6067747 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19