Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 983 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1593. Min Range: -8.1593
Max Act: 8.1593. Min Act: -0.1700
Data Index: 7234960 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1593. Min Range: -8.1593
Max Act: 8.0343. Min Act: -0.1700
Data Index: 1875517 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.9718. Min Act: -0.1700
Data Index: 4242159 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.9093. Min Act: -0.1700
Data Index: 5444642 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.9093. Min Act: -0.1700
Data Index: 6839006 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.8468. Min Act: -0.1700
Data Index: 7730212 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.8468. Min Act: -0.1700
Data Index: 3347828 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.7843. Min Act: -0.1700
Data Index: 7633375 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.7843. Min Act: -0.1700
Data Index: 5529589 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.7218. Min Act: -0.1700
Data Index: 1408504 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.7218. Min Act: -0.1700
Data Index: 3839509 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.7218. Min Act: -0.1700
Data Index: 7730211 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.6593. Min Act: -0.1700
Data Index: 1929331 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.6593. Min Act: -0.1700
Data Index: 4099802 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.5968. Min Act: -0.1700
Data Index: 3169639 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.5968. Min Act: -0.1700
Data Index: 5640921 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.5968. Min Act: -0.1700
Data Index: 5005461 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.5968. Min Act: -0.1700
Data Index: 4587209 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.6593. Min Act: -0.1700
Data Index: 1663975 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1593. Min Range: -8.1593
Max Act: 7.5343. Min Act: -0.1700
Data Index: 1672431 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19