Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1936 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.8937. Min Act: -0.1700
Data Index: 1702738 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.6124. Min Act: -0.1700
Data Index: 3409372 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.4874. Min Act: -0.1700
Data Index: 7676638 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.4874. Min Act: -0.1700
Data Index: 3794448 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.4562. Min Act: -0.1700
Data Index: 3259382 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.4562. Min Act: -0.1700
Data Index: 6348324 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.4249. Min Act: -0.1700
Data Index: 8172369 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.4562. Min Act: -0.1700
Data Index: 4849386 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.3937. Min Act: -0.1700
Data Index: 3317059 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.2999. Min Act: -0.1700
Data Index: 5280904 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.2687. Min Act: -0.1700
Data Index: 7364839 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.2374. Min Act: -0.1700
Data Index: 2233313 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.2374. Min Act: -0.1700
Data Index: 5921766 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.2374. Min Act: -0.1700
Data Index: 1334195 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.2062. Min Act: -0.1700
Data Index: 7362793 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.2062. Min Act: -0.1700
Data Index: 5476656 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.1749. Min Act: -0.1700
Data Index: 655605 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.1749. Min Act: -0.1700
Data Index: 7488753 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.1749. Min Act: -0.1700
Data Index: 3413292 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8937. Min Range: -6.8937
Max Act: 6.1437. Min Act: -0.1700
Data Index: 6404315 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19