Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.9181. Min Act: -0.1700
Data Index: 6974638 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4806. Min Act: -0.1700
Data Index: 6363502 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4806. Min Act: -0.1700
Data Index: 2925047 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4181. Min Act: -0.1700
Data Index: 1526805 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4181. Min Act: -0.1700
Data Index: 1435016 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.3556. Min Act: -0.1700
Data Index: 4347341 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.3869. Min Act: -0.1700
Data Index: 383628 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.3556. Min Act: -0.1700
Data Index: 801712 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.3244. Min Act: -0.1700
Data Index: 5278843 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.2931. Min Act: -0.1700
Data Index: 7173403 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.2619. Min Act: -0.1700
Data Index: 8478697 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.1994. Min Act: -0.1700
Data Index: 1941235 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5136745 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.1056. Min Act: -0.1700
Data Index: 539422 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.1681. Min Act: -0.1700
Data Index: 6684432 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.1369. Min Act: -0.1700
Data Index: 4498629 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.1056. Min Act: -0.1700
Data Index: 448951 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.0744. Min Act: -0.1700
Data Index: 520605 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.0431. Min Act: -0.1700
Data Index: 4620198 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.0431. Min Act: -0.1700
Data Index: 1022865 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19