Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2495 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.9508. Min Act: -0.1700
Data Index: 1651376 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.8883. Min Act: -0.1700
Data Index: 5777522 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7945. Min Act: -0.1700
Data Index: 6894440 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7633. Min Act: -0.1700
Data Index: 8083150 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7633. Min Act: -0.1700
Data Index: 678201 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7320. Min Act: -0.1700
Data Index: 2215086 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7008. Min Act: -0.1700
Data Index: 3785990 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4179998 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7320. Min Act: -0.1700
Data Index: 5652035 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.7008. Min Act: -0.1700
Data Index: 5325351 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.6695. Min Act: -0.1700
Data Index: 6134599 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.6695. Min Act: -0.1700
Data Index: 5644810 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.6383. Min Act: -0.1700
Data Index: 6650882 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.6070. Min Act: -0.1700
Data Index: 5582824 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.5758. Min Act: -0.1700
Data Index: 3756117 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.5758. Min Act: -0.1700
Data Index: 4203582 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.5445. Min Act: -0.1700
Data Index: 7262786 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.5133. Min Act: -0.1700
Data Index: 2332381 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.5133. Min Act: -0.1700
Data Index: 5492425 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9508. Min Range: -5.9508
Max Act: 5.5133. Min Act: -0.1700
Data Index: 5967086 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19