Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 691 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5383. Min Range: -8.5383
Max Act: 8.5383. Min Act: -0.1700
Data Index: 2388480 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5383. Min Range: -8.5383
Max Act: 8.5383. Min Act: -0.1700
Data Index: 298318 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5383. Min Range: -8.5383
Max Act: 8.2258. Min Act: -0.1700
Data Index: 2368536 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5383. Min Range: -8.5383
Max Act: 8.1633. Min Act: -0.1700
Data Index: 170268 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5383. Min Range: -8.5383
Max Act: 8.1008. Min Act: -0.1700
Data Index: 1135171 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.9133. Min Act: -0.1700
Data Index: 8267756 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.9133. Min Act: -0.1700
Data Index: 4369616 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.9133. Min Act: -0.1700
Data Index: 7503688 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.8508. Min Act: -0.1700
Data Index: 4972987 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.8508. Min Act: -0.1700
Data Index: 6178933 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.7258. Min Act: -0.1700
Data Index: 5889070 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.7258. Min Act: -0.1700
Data Index: 8703983 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.6633. Min Act: -0.1700
Data Index: 2070193 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.6633. Min Act: -0.1700
Data Index: 2151082 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.5695. Min Act: -0.1700
Data Index: 1153694 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.6008. Min Act: -0.1700
Data Index: 996515 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.6008. Min Act: -0.1700
Data Index: 6402991 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.5695. Min Act: -0.1700
Data Index: 1893173 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.5695. Min Act: -0.1700
Data Index: 7288980 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5383. Min Range: -8.5383
Max Act: 7.5695. Min Act: -0.1700
Data Index: 8685290 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19