Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.5813. Min Act: -0.1700
Data Index: 6545076 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.5813. Min Act: -0.1700
Data Index: 5753184 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.5188. Min Act: -0.1700
Data Index: 5966 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.5188. Min Act: -0.1700
Data Index: 2324590 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.5188. Min Act: -0.1700
Data Index: 1813363 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.4250. Min Act: -0.1700
Data Index: 3974069 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.4250. Min Act: -0.1700
Data Index: 4340465 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.4250. Min Act: -0.1700
Data Index: 3011914 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3938. Min Act: -0.1700
Data Index: 3970327 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.4250. Min Act: -0.1700
Data Index: 4195486 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3625. Min Act: -0.1700
Data Index: 6201518 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3625. Min Act: -0.1700
Data Index: 3970328 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3625. Min Act: -0.1700
Data Index: 6098216 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3625. Min Act: -0.1700
Data Index: 7999496 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3313. Min Act: -0.1700
Data Index: 7489249 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3313. Min Act: -0.1700
Data Index: 5269305 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3313. Min Act: -0.1700
Data Index: 6545074 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3313. Min Act: -0.1700
Data Index: 1776237 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.3000. Min Act: -0.1700
Data Index: 3630493 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5813. Min Range: -6.5813
Max Act: 6.2688. Min Act: -0.1700
Data Index: 7648029 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19