Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1240. Min Range: -6.1240
Max Act: 6.1240. Min Act: -0.1700
Data Index: 115307 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1240. Min Range: -6.1240
Max Act: 6.0615. Min Act: -0.1700
Data Index: 8352660 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.9990. Min Act: -0.1700
Data Index: 3468627 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.9365. Min Act: -0.1700
Data Index: 3018089 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.9053. Min Act: -0.1700
Data Index: 6763884 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8740. Min Act: -0.1700
Data Index: 3058030 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8740. Min Act: -0.1700
Data Index: 6795015 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8740. Min Act: -0.1700
Data Index: 145105 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8428. Min Act: -0.1700
Data Index: 7766573 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8115. Min Act: -0.1700
Data Index: 8222974 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8428. Min Act: -0.1700
Data Index: 3381019 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.7803. Min Act: -0.1700
Data Index: 5179896 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8115. Min Act: -0.1700
Data Index: 5013849 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8428. Min Act: -0.1700
Data Index: 7393965 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.7803. Min Act: -0.1700
Data Index: 2630928 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.7803. Min Act: -0.1700
Data Index: 4000261 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.7803. Min Act: -0.1700
Data Index: 2795973 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.7803. Min Act: -0.1700
Data Index: 7733059 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.8115. Min Act: -0.1700
Data Index: 6763883 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1240. Min Range: -6.1240
Max Act: 5.7490. Min Act: -0.1700
Data Index: 5676953 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19