Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.7537. Min Act: -0.1700
Data Index: 985183 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.6599. Min Act: -0.1700
Data Index: 7183397 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.6599. Min Act: -0.1700
Data Index: 4039760 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5974. Min Act: -0.1700
Data Index: 5507689 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.6287. Min Act: -0.1700
Data Index: 1733873 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.6287. Min Act: -0.1700
Data Index: 6134605 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.6287. Min Act: -0.1700
Data Index: 7914939 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5662. Min Act: -0.1700
Data Index: 2856479 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5974. Min Act: -0.1700
Data Index: 5085849 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5662. Min Act: -0.1700
Data Index: 5507281 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5662. Min Act: -0.1700
Data Index: 3509318 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5662. Min Act: -0.1700
Data Index: 91452 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5349. Min Act: -0.1700
Data Index: 7536092 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5349. Min Act: -0.1700
Data Index: 4073586 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5349. Min Act: -0.1700
Data Index: 5623979 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5662. Min Act: -0.1700
Data Index: 4073585 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5349. Min Act: -0.1700
Data Index: 1836940 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5037. Min Act: -0.1700
Data Index: 6352290 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5037. Min Act: -0.1700
Data Index: 1702018 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7537. Min Range: -5.7537
Max Act: 5.5037. Min Act: -0.1700
Data Index: 3021602 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19