Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4479. Min Range: -9.4479
Max Act: 9.4479. Min Act: -0.1700
Data Index: 7092634 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4479. Min Range: -9.4479
Max Act: 8.1354. Min Act: -0.1700
Data Index: 2438940 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4479. Min Range: -9.4479
Max Act: 8.1354. Min Act: -0.1700
Data Index: 4111332 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4479. Min Range: -9.4479
Max Act: 8.1354. Min Act: -0.1700
Data Index: 7121077 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4479. Min Range: -9.4479
Max Act: 8.1354. Min Act: -0.1700
Data Index: 5957406 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.9479. Min Act: -0.1700
Data Index: 262798 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.9479. Min Act: -0.1700
Data Index: 1569056 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.8854. Min Act: -0.1700
Data Index: 6526237 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.7604. Min Act: -0.1700
Data Index: 2127829 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.7292. Min Act: -0.1700
Data Index: 167723 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.6667. Min Act: -0.1700
Data Index: 1550136 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.6667. Min Act: -0.1700
Data Index: 8018779 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.6354. Min Act: -0.1700
Data Index: 8743436 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.6042. Min Act: -0.1700
Data Index: 4857253 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.6354. Min Act: -0.1700
Data Index: 6766263 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.6354. Min Act: -0.1700
Data Index: 5772756 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.6042. Min Act: -0.1700
Data Index: 1772370 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.5729. Min Act: -0.1700
Data Index: 1524774 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.5417. Min Act: -0.1700
Data Index: 829772 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4479. Min Range: -9.4479
Max Act: 7.5729. Min Act: -0.1700
Data Index: 7966228 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19