Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.9270. Min Act: -0.1700
Data Index: 6362281 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.8020. Min Act: -0.1700
Data Index: 6109157 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.8020. Min Act: -0.1700
Data Index: 4145690 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.7395. Min Act: -0.1700
Data Index: 4360008 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.7395. Min Act: -0.1700
Data Index: 5314021 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.7082. Min Act: -0.1700
Data Index: 2696443 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.6770. Min Act: -0.1700
Data Index: 7871389 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.5832. Min Act: -0.1700
Data Index: 934404 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.6457. Min Act: -0.1700
Data Index: 6663880 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.6145. Min Act: -0.1700
Data Index: 5909641 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.5832. Min Act: -0.1700
Data Index: 6592725 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.5207. Min Act: -0.1700
Data Index: 8141780 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.5207. Min Act: -0.1700
Data Index: 7339798 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.4582. Min Act: -0.1700
Data Index: 2004200 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.4895. Min Act: -0.1700
Data Index: 800467 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.4582. Min Act: -0.1700
Data Index: 2239203 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.4270. Min Act: -0.1700
Data Index: 1068332 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.4270. Min Act: -0.1700
Data Index: 8483011 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.3645. Min Act: -0.1700
Data Index: 7748285 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9270. Min Range: -6.9270
Max Act: 6.3332. Min Act: -0.1700
Data Index: 5151684 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19