Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1231. Min Range: -4.1231
Max Act: 4.1231. Min Act: -0.1700
Data Index: 4221406 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1231. Min Range: -4.1231
Max Act: 4.0293. Min Act: -0.1700
Data Index: 1460133 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9981. Min Act: -0.1700
Data Index: 3786303 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9981. Min Act: -0.1700
Data Index: 6510486 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9668. Min Act: -0.1700
Data Index: 4010500 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9355. Min Act: -0.1700
Data Index: 5114697 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9043. Min Act: -0.1700
Data Index: 1943788 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.9043. Min Act: -0.1700
Data Index: 7650967 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8417. Min Act: -0.1700
Data Index: 30179 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8730. Min Act: -0.1700
Data Index: 5267444 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8730. Min Act: -0.1700
Data Index: 8649749 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8417. Min Act: -0.1700
Data Index: 7468337 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 3931097 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8417. Min Act: -0.1700
Data Index: 8692180 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8417. Min Act: -0.1700
Data Index: 4444107 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8417. Min Act: -0.1700
Data Index: 7127189 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 2039453 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 1850720 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 338315 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1231. Min Range: -4.1231
Max Act: 3.8105. Min Act: -0.1700
Data Index: 3115325 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19