Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.9270. Min Act: -0.1700
Data Index: 4110980 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.8644. Min Act: -0.1700
Data Index: 6315810 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.8332. Min Act: -0.1700
Data Index: 966386 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.8175. Min Act: -0.1700
Data Index: 7500578 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.8175. Min Act: -0.1700
Data Index: 1922442 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.8175. Min Act: -0.1700
Data Index: 484635 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.8019. Min Act: -0.1700
Data Index: 5102803 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.7706. Min Act: -0.1700
Data Index: 5979149 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.7706. Min Act: -0.1700
Data Index: 5382699 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.7706. Min Act: -0.1700
Data Index: 8243660 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.7706. Min Act: -0.1700
Data Index: 3841472 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.7237. Min Act: -0.1700
Data Index: 4166322 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.7081. Min Act: -0.1700
Data Index: 6535719 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.6924. Min Act: -0.1700
Data Index: 288678 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.6924. Min Act: -0.1700
Data Index: 8229728 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.6611. Min Act: -0.1700
Data Index: 5332379 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.6611. Min Act: -0.1700
Data Index: 1559200 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.6455. Min Act: -0.1700
Data Index: 7489575 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.6298. Min Act: -0.1700
Data Index: 33707 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9270. Min Range: -3.9270
Max Act: 3.6298. Min Act: -0.1700
Data Index: 5083260 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19