Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1790 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.3854. Min Act: -0.1700
Data Index: 6598888 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.3540. Min Act: -0.1700
Data Index: 957855 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.3383. Min Act: -0.1700
Data Index: 1274460 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.3383. Min Act: -0.1700
Data Index: 7683375 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.3383. Min Act: -0.1700
Data Index: 8190446 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.3070. Min Act: -0.1700
Data Index: 1758647 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2913. Min Act: -0.1700
Data Index: 7207942 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2913. Min Act: -0.1700
Data Index: 164550 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2598. Min Act: -0.1700
Data Index: 4763991 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2598. Min Act: -0.1700
Data Index: 3584535 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2441. Min Act: -0.1700
Data Index: 999371 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2284. Min Act: -0.1700
Data Index: 8277842 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2441. Min Act: -0.1700
Data Index: 3774612 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2284. Min Act: -0.1700
Data Index: 112166 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2284. Min Act: -0.1700
Data Index: 6109597 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2127. Min Act: -0.1700
Data Index: 5070053 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2284. Min Act: -0.1700
Data Index: 2426999 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2284. Min Act: -0.1700
Data Index: 60822 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2127. Min Act: -0.1700
Data Index: 4103392 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3854. Min Range: -3.3854
Max Act: 3.2127. Min Act: -0.1700
Data Index: 5695159 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19