Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0395. Min Range: -9.0395
Max Act: 9.0395. Min Act: -0.1700
Data Index: 8568255 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0395. Min Range: -9.0395
Max Act: 8.4145. Min Act: -0.1700
Data Index: 7105512 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0395. Min Range: -9.0395
Max Act: 8.0708. Min Act: -0.1700
Data Index: 3232423 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.9770. Min Act: -0.1700
Data Index: 1021723 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.8833. Min Act: -0.1700
Data Index: 1087244 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.8833. Min Act: -0.1700
Data Index: 1865060 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.8833. Min Act: -0.1700
Data Index: 1550680 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.7583. Min Act: -0.1700
Data Index: 291492 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.7583. Min Act: -0.1700
Data Index: 5154564 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.7270. Min Act: -0.1700
Data Index: 6099947 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.7895. Min Act: -0.1700
Data Index: 223740 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.7270. Min Act: -0.1700
Data Index: 6815475 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.7270. Min Act: -0.1700
Data Index: 1129018 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.7270. Min Act: -0.1700
Data Index: 6339453 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.6958. Min Act: -0.1700
Data Index: 223739 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.6333. Min Act: -0.1700
Data Index: 8458410 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.6333. Min Act: -0.1700
Data Index: 983684 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.6020. Min Act: -0.1700
Data Index: 4857946 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.5708. Min Act: -0.1700
Data Index: 3807723 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0395. Min Range: -9.0395
Max Act: 7.6020. Min Act: -0.1700
Data Index: 393574 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19