Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.9039. Min Act: -0.1700
Data Index: 3304729 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.8727. Min Act: -0.1700
Data Index: 8212745 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.8102. Min Act: -0.1700
Data Index: 3848937 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.7477. Min Act: -0.1700
Data Index: 8771562 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.6852. Min Act: -0.1700
Data Index: 8323629 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.6852. Min Act: -0.1700
Data Index: 774564 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.6852. Min Act: -0.1700
Data Index: 7025563 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.6539. Min Act: -0.1700
Data Index: 4555261 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.6227. Min Act: -0.1700
Data Index: 4932701 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.6539. Min Act: -0.1700
Data Index: 2033991 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.6227. Min Act: -0.1700
Data Index: 2802191 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.5602. Min Act: -0.1700
Data Index: 722389 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.5914. Min Act: -0.1700
Data Index: 616163 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.5914. Min Act: -0.1700
Data Index: 7538506 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.5914. Min Act: -0.1699
Data Index: 3830637 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.5289. Min Act: -0.1700
Data Index: 1961229 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.4977. Min Act: -0.1700
Data Index: 2689327 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.5289. Min Act: -0.1700
Data Index: 3006864 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.4977. Min Act: -0.1700
Data Index: 1670793 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9039. Min Range: -6.9039
Max Act: 6.4977. Min Act: -0.1699
Data Index: 3919678 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19