Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.5653. Min Act: -0.1700
Data Index: 5924170 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.5028. Min Act: -0.1700
Data Index: 5924168 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.3466. Min Act: -0.1700
Data Index: 2661900 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.2841. Min Act: -0.1700
Data Index: 1476273 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.2216. Min Act: -0.1700
Data Index: 7409681 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.1278. Min Act: -0.1700
Data Index: 1679879 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.0966. Min Act: -0.1700
Data Index: 6411952 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.0653. Min Act: -0.1700
Data Index: 4800005 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.0341. Min Act: -0.1700
Data Index: 7111295 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5653. Min Range: -7.5653
Max Act: 7.0028. Min Act: -0.1700
Data Index: 8235521 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9716. Min Act: -0.1700
Data Index: 8638878 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9716. Min Act: -0.1700
Data Index: 6848823 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9716. Min Act: -0.1700
Data Index: 5796574 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9403. Min Act: -0.1700
Data Index: 2613741 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9403. Min Act: -0.1700
Data Index: 5878790 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9403. Min Act: -0.1700
Data Index: 4524252 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9091. Min Act: -0.1700
Data Index: 6234137 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.9091. Min Act: -0.1700
Data Index: 3708124 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.8778. Min Act: -0.1700
Data Index: 529152 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5653. Min Range: -7.5653
Max Act: 6.8466. Min Act: -0.1700
Data Index: 330275 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19