Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9950. Min Act: -0.1700
Data Index: 8553532 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9781. Min Act: -0.1700
Data Index: 5025699 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9781. Min Act: -0.1700
Data Index: 5180000 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9781. Min Act: -0.1700
Data Index: 6194710 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9612. Min Act: -0.1700
Data Index: 7513083 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9612. Min Act: -0.1700
Data Index: 6683730 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9612. Min Act: -0.1700
Data Index: 3910636 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9527. Min Act: -0.1700
Data Index: 1231775 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9527. Min Act: -0.1700
Data Index: 849982 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9357. Min Act: -0.1700
Data Index: 2773748 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9527. Min Act: -0.1700
Data Index: 2780522 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9357. Min Act: -0.1699
Data Index: 140857 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9442. Min Act: -0.1700
Data Index: 1943995 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9442. Min Act: -0.1700
Data Index: 5172541 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9272. Min Act: -0.1700
Data Index: 1561968 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9357. Min Act: -0.1700
Data Index: 1831211 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9272. Min Act: -0.1698
Data Index: 4182921 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9272. Min Act: -0.1700
Data Index: 6109222 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9272. Min Act: -0.1700
Data Index: 6134533 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9950. Min Range: -1.9950
Max Act: 1.9272. Min Act: -0.1700
Data Index: 4700886 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19