Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.9481. Min Act: -0.1700
Data Index: 4890300 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.9169. Min Act: -0.1700
Data Index: 7477511 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.8544. Min Act: -0.1700
Data Index: 4865982 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.8856. Min Act: -0.1700
Data Index: 6590240 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.8231. Min Act: -0.1700
Data Index: 5876723 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.7919. Min Act: -0.1700
Data Index: 2585116 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.7606. Min Act: -0.1700
Data Index: 2280527 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.7294. Min Act: -0.1700
Data Index: 5129483 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.7294. Min Act: -0.1700
Data Index: 5959222 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6669. Min Act: -0.1700
Data Index: 1457899 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6669. Min Act: -0.1700
Data Index: 327760 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6669. Min Act: -0.1700
Data Index: 7533098 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6669. Min Act: -0.1700
Data Index: 3460568 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6356. Min Act: -0.1700
Data Index: 3979843 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6356. Min Act: -0.1700
Data Index: 5139140 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6356. Min Act: -0.1700
Data Index: 687227 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6044. Min Act: -0.1700
Data Index: 6528196 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6044. Min Act: -0.1700
Data Index: 1737868 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6044. Min Act: -0.1700
Data Index: 758700 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9481. Min Range: -5.9481
Max Act: 5.6044. Min Act: -0.1700
Data Index: 5219270 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19