Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4966 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.8938. Min Act: -0.1700
Data Index: 5630076 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.7688. Min Act: -0.1700
Data Index: 445343 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.8313. Min Act: -0.1700
Data Index: 4792940 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.7688. Min Act: -0.1700
Data Index: 4674637 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.6438. Min Act: -0.1700
Data Index: 5198186 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.5813. Min Act: -0.1700
Data Index: 6410931 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.5188. Min Act: -0.1700
Data Index: 4354354 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.5188. Min Act: -0.1700
Data Index: 870953 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.5188. Min Act: -0.1700
Data Index: 2170695 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.4563. Min Act: -0.1700
Data Index: 5556276 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.4563. Min Act: -0.1700
Data Index: 165753 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.4563. Min Act: -0.1700
Data Index: 7797246 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.4563. Min Act: -0.1700
Data Index: 5225972 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.4563. Min Act: -0.1700
Data Index: 4204374 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.3938. Min Act: -0.1700
Data Index: 4117584 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.3938. Min Act: -0.1700
Data Index: 6747435 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.3938. Min Act: -0.1700
Data Index: 2792221 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.3938. Min Act: -0.1700
Data Index: 5531001 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.3313. Min Act: -0.1700
Data Index: 833291 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8938. Min Range: -9.8938
Max Act: 9.3313. Min Act: -0.1700
Data Index: 1282994 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19