Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4499 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5438. Min Range: -5.5438
Max Act: 5.5438. Min Act: -0.1700
Data Index: 2552115 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5438. Min Range: -5.5438
Max Act: 5.3875. Min Act: -0.1700
Data Index: 7700108 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5438. Min Range: -5.5438
Max Act: 5.1375. Min Act: -0.1700
Data Index: 4105156 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5438. Min Range: -5.5438
Max Act: 5.0750. Min Act: -0.1700
Data Index: 2630761 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5438. Min Range: -5.5438
Max Act: 5.0125. Min Act: -0.1700
Data Index: 5060886 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8875. Min Act: -0.1700
Data Index: 623081 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8875. Min Act: -0.1700
Data Index: 8346299 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8875. Min Act: -0.1700
Data Index: 8297879 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8250. Min Act: -0.1700
Data Index: 1148263 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4800380 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8563. Min Act: -0.1700
Data Index: 7935889 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8250. Min Act: -0.1700
Data Index: 5446328 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.8250. Min Act: -0.1700
Data Index: 636170 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.7625. Min Act: -0.1700
Data Index: 996578 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.7625. Min Act: -0.1700
Data Index: 1666389 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.7313. Min Act: -0.1700
Data Index: 1055115 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.7313. Min Act: -0.1700
Data Index: 1055404 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.7313. Min Act: -0.1700
Data Index: 4707598 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.7000. Min Act: -0.1700
Data Index: 2269321 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5438. Min Range: -5.5438
Max Act: 4.6375. Min Act: -0.1700
Data Index: 2620402 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19