Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5835 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.6415. Min Act: -0.1700
Data Index: 4730564 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.5477. Min Act: -0.1700
Data Index: 5348383 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.4227. Min Act: -0.1700
Data Index: 6774530 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.3602. Min Act: -0.1700
Data Index: 5780154 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.3915. Min Act: -0.1700
Data Index: 8382156 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.3602. Min Act: -0.1700
Data Index: 4869836 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.3602. Min Act: -0.1700
Data Index: 3859148 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.3602. Min Act: -0.1700
Data Index: 2857131 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2977. Min Act: -0.1700
Data Index: 1753095 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2977. Min Act: -0.1700
Data Index: 3927515 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2665. Min Act: -0.1700
Data Index: 3690813 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2665. Min Act: -0.1700
Data Index: 4829811 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2665. Min Act: -0.1700
Data Index: 4317275 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2665. Min Act: -0.1700
Data Index: 6516992 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2665. Min Act: -0.1700
Data Index: 3350362 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2352. Min Act: -0.1700
Data Index: 7031553 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2352. Min Act: -0.1700
Data Index: 8101676 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2352. Min Act: -0.1700
Data Index: 6604254 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2352. Min Act: -0.1700
Data Index: 3390186 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6415. Min Range: -5.6415
Max Act: 5.2352. Min Act: -0.1700
Data Index: 8157995 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19