Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.9176. Min Act: -0.1700
Data Index: 1268071 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.8864. Min Act: -0.1700
Data Index: 3115132 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.8238. Min Act: -0.1700
Data Index: 617102 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7926. Min Act: -0.1700
Data Index: 325972 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.8238. Min Act: -0.1700
Data Index: 5085949 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7926. Min Act: -0.1700
Data Index: 4957601 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7613. Min Act: -0.1700
Data Index: 3115130 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7300. Min Act: -0.1700
Data Index: 5043601 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7613. Min Act: -0.1700
Data Index: 3552223 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7613. Min Act: -0.1700
Data Index: 758168 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7300. Min Act: -0.1700
Data Index: 2704138 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7300. Min Act: -0.1700
Data Index: 2932176 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.6987. Min Act: -0.1700
Data Index: 3450372 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7300. Min Act: -0.1700
Data Index: 1784889 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7300. Min Act: -0.1700
Data Index: 5230886 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7613. Min Act: -0.1700
Data Index: 2819141 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7300. Min Act: -0.1700
Data Index: 7459503 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.7300. Min Act: -0.1700
Data Index: 2348682 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.6987. Min Act: -0.1700
Data Index: 331281 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9176. Min Range: -3.9176
Max Act: 3.6987. Min Act: -0.1700
Data Index: 2697114 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19