Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.3516. Min Act: -0.1700
Data Index: 6983495 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.3680. Min Act: -0.1700
Data Index: 3844273 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.3188. Min Act: -0.1700
Data Index: 19932 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.3352. Min Act: -0.1700
Data Index: 8162840 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.3188. Min Act: -0.1700
Data Index: 106070 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.3188. Min Act: -0.1700
Data Index: 3815817 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.4006. Min Act: -0.1700
Data Index: 5380593 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2859. Min Act: -0.1700
Data Index: 7137573 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2364. Min Act: -0.1700
Data Index: 5103932 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2859. Min Act: -0.1700
Data Index: 1415839 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2694. Min Act: -0.1700
Data Index: 7435120 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.3188. Min Act: -0.1700
Data Index: 7652121 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2198. Min Act: -0.1700
Data Index: 5754222 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2694. Min Act: -0.1700
Data Index: 1694369 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2694. Min Act: -0.1700
Data Index: 7586908 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2694. Min Act: -0.1700
Data Index: 1591984 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2694. Min Act: -0.1700
Data Index: 4598916 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2694. Min Act: -0.1700
Data Index: 5791653 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.2198. Min Act: -0.1700
Data Index: 2726173 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4006. Min Range: -2.4006
Max Act: 2.1534. Min Act: -0.1700
Data Index: 7347895 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19