Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1619 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6983. Min Range: -7.6983
Max Act: 7.6983. Min Act: -0.1700
Data Index: 6531716 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6983. Min Range: -7.6983
Max Act: 7.3858. Min Act: -0.1700
Data Index: 682229 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6983. Min Range: -7.6983
Max Act: 7.4483. Min Act: -0.1700
Data Index: 1442296 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.9795. Min Act: -0.1700
Data Index: 6916245 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.9795. Min Act: -0.1700
Data Index: 3683436 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 117885 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 273385 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.7920. Min Act: -0.1700
Data Index: 8671548 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.7295. Min Act: -0.1700
Data Index: 5879911 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.6670. Min Act: -0.1700
Data Index: 5239647 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.6358. Min Act: -0.1700
Data Index: 8372601 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.5733. Min Act: -0.1700
Data Index: 1767902 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.5733. Min Act: -0.1700
Data Index: 1938589 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.5420. Min Act: -0.1700
Data Index: 4432517 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.5420. Min Act: -0.1700
Data Index: 8140587 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.5420. Min Act: -0.1700
Data Index: 8609407 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.5420. Min Act: -0.1700
Data Index: 2737444 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.5108. Min Act: -0.1700
Data Index: 2018035 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.4483. Min Act: -0.1700
Data Index: 6465404 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6983. Min Range: -7.6983
Max Act: 6.3858. Min Act: -0.1700
Data Index: 3390718 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19