Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2399 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2796. Min Act: -0.1700
Data Index: 2817483 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2639. Min Act: -0.1700
Data Index: 4918972 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2325. Min Act: -0.1700
Data Index: 7360677 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2168. Min Act: -0.1700
Data Index: 3372892 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2168. Min Act: -0.1700
Data Index: 3190018 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2168. Min Act: -0.1700
Data Index: 7413264 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2168. Min Act: -0.1700
Data Index: 205126 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2325. Min Act: -0.1700
Data Index: 6507010 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2011. Min Act: -0.1700
Data Index: 8275261 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2011. Min Act: -0.1700
Data Index: 3866216 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1853. Min Act: -0.1700
Data Index: 3536315 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1853. Min Act: -0.1700
Data Index: 6015647 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.2011. Min Act: -0.1700
Data Index: 86762 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1696. Min Act: -0.1700
Data Index: 7316280 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1853. Min Act: -0.1700
Data Index: 2011415 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1696. Min Act: -0.1700
Data Index: 5839038 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1853. Min Act: -0.1700
Data Index: 4910887 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1853. Min Act: -0.1700
Data Index: 277190 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1696. Min Act: -0.1700
Data Index: 1889409 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2796. Min Range: -3.2796
Max Act: 3.1853. Min Act: -0.1700
Data Index: 5795758 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19