Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2146. Min Range: -6.2146
Max Act: 6.2146. Min Act: -0.1700
Data Index: 696723 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2146. Min Range: -6.2146
Max Act: 6.1834. Min Act: -0.1700
Data Index: 8235852 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2146. Min Range: -6.2146
Max Act: 6.1209. Min Act: -0.1700
Data Index: 7415193 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2146. Min Range: -6.2146
Max Act: 6.0271. Min Act: -0.1700
Data Index: 8106546 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9959. Min Act: -0.1700
Data Index: 6284299 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9334. Min Act: -0.1700
Data Index: 3996235 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9334. Min Act: -0.1700
Data Index: 581723 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9334. Min Act: -0.1700
Data Index: 4059142 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9334. Min Act: -0.1700
Data Index: 530833 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9334. Min Act: -0.1700
Data Index: 5682356 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9334. Min Act: -0.1700
Data Index: 5629247 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9021. Min Act: -0.1700
Data Index: 2938827 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.9021. Min Act: -0.1700
Data Index: 7670832 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.8709. Min Act: -0.1700
Data Index: 3392907 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.8709. Min Act: -0.1700
Data Index: 3476906 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.8084. Min Act: -0.1700
Data Index: 7915594 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6477395 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.8084. Min Act: -0.1700
Data Index: 5473229 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.8396. Min Act: -0.1700
Data Index: 1595235 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2146. Min Range: -6.2146
Max Act: 5.8396. Min Act: -0.1700
Data Index: 5236938 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19