Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.9243. Min Act: -0.1700
Data Index: 4154774 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8986. Min Act: -0.1700
Data Index: 6174318 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.9157. Min Act: -0.1700
Data Index: 3715873 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.9072. Min Act: -0.1700
Data Index: 125213 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8901. Min Act: -0.1700
Data Index: 4755884 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8901. Min Act: -0.1700
Data Index: 5584481 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8901. Min Act: -0.1700
Data Index: 5398370 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8901. Min Act: -0.1700
Data Index: 5530221 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8901. Min Act: -0.1700
Data Index: 7594989 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8901. Min Act: -0.1700
Data Index: 1788457 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8815. Min Act: -0.1700
Data Index: 626364 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8730. Min Act: -0.1700
Data Index: 8191190 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8815. Min Act: -0.1700
Data Index: 7179341 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8645. Min Act: -0.1700
Data Index: 1852456 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8730. Min Act: -0.1700
Data Index: 1144290 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8730. Min Act: -0.1700
Data Index: 3333886 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8730. Min Act: -0.1700
Data Index: 1886527 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8730. Min Act: -0.1700
Data Index: 6803684 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8730. Min Act: -0.1700
Data Index: 2012022 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9243. Min Range: -0.9243
Max Act: 0.8645. Min Act: -0.1700
Data Index: 296126 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19