Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6217. Min Range: -8.6217
Max Act: 8.6217. Min Act: -0.1700
Data Index: 1223610 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6217. Min Range: -8.6217
Max Act: 8.3717. Min Act: -0.1700
Data Index: 4179417 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6217. Min Range: -8.6217
Max Act: 8.1217. Min Act: -0.1700
Data Index: 5843279 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6217. Min Range: -8.6217
Max Act: 8.0280. Min Act: -0.1700
Data Index: 92150 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.9967. Min Act: -0.1700
Data Index: 3621002 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8717. Min Act: -0.1700
Data Index: 7409565 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.9342. Min Act: -0.1700
Data Index: 7423075 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8092. Min Act: -0.1700
Data Index: 4109862 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8717. Min Act: -0.1700
Data Index: 2665355 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8405. Min Act: -0.1700
Data Index: 877832 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8405. Min Act: -0.1700
Data Index: 7586134 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8405. Min Act: -0.1700
Data Index: 2642608 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8405. Min Act: -0.1700
Data Index: 8216010 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8092. Min Act: -0.1700
Data Index: 7048449 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.7780. Min Act: -0.1700
Data Index: 6001328 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.8092. Min Act: -0.1700
Data Index: 7279126 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.7780. Min Act: -0.1700
Data Index: 3817329 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.7467. Min Act: -0.1700
Data Index: 538762 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.6842. Min Act: -0.1700
Data Index: 78377 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6217. Min Range: -8.6217
Max Act: 7.6842. Min Act: -0.1700
Data Index: 3083855 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19