Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0389. Min Range: -8.0389
Max Act: 8.0389. Min Act: -0.1700
Data Index: 835620 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0389. Min Range: -8.0389
Max Act: 8.0389. Min Act: -0.1700
Data Index: 6609864 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.9139. Min Act: -0.1700
Data Index: 8198582 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.8826. Min Act: -0.1700
Data Index: 4512330 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.8201. Min Act: -0.1700
Data Index: 6686230 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.7889. Min Act: -0.1700
Data Index: 1912222 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.7576. Min Act: -0.1700
Data Index: 4913321 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.6951. Min Act: -0.1700
Data Index: 2105470 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.6951. Min Act: -0.1700
Data Index: 267384 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.6951. Min Act: -0.1700
Data Index: 4913320 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.6639. Min Act: -0.1700
Data Index: 1912223 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.6326. Min Act: -0.1700
Data Index: 211538 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.5076. Min Act: -0.1700
Data Index: 5289854 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.5389. Min Act: -0.1700
Data Index: 3984471 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.5076. Min Act: -0.1700
Data Index: 421265 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.5701. Min Act: -0.1700
Data Index: 211550 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.5076. Min Act: -0.1700
Data Index: 1515695 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.4764. Min Act: -0.1700
Data Index: 8293176 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.4451. Min Act: -0.1700
Data Index: 5501606 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0389. Min Range: -8.0389
Max Act: 7.4139. Min Act: -0.1700
Data Index: 1601031 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19