Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.7174. Min Act: -0.1700
Data Index: 5133532 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.6549. Min Act: -0.1700
Data Index: 7849241 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.6237. Min Act: -0.1700
Data Index: 4854065 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.5924. Min Act: -0.1700
Data Index: 2398939 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.5612. Min Act: -0.1700
Data Index: 5500936 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.5299. Min Act: -0.1700
Data Index: 515809 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4987. Min Act: -0.1700
Data Index: 8774771 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4987. Min Act: -0.1700
Data Index: 2953832 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4674. Min Act: -0.1700
Data Index: 395913 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4674. Min Act: -0.1700
Data Index: 6376654 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4362. Min Act: -0.1700
Data Index: 7409265 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4362. Min Act: -0.1700
Data Index: 1160996 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4362. Min Act: -0.1700
Data Index: 2419046 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4362. Min Act: -0.1700
Data Index: 4531723 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4049. Min Act: -0.1700
Data Index: 1300615 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4049. Min Act: -0.1700
Data Index: 8802452 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.4362. Min Act: -0.1700
Data Index: 234429 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.3737. Min Act: -0.1700
Data Index: 4569036 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.3424. Min Act: -0.1700
Data Index: 4583961 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7174. Min Range: -5.7174
Max Act: 5.3737. Min Act: -0.1700
Data Index: 4604417 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19