Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3964 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.5684. Min Act: -0.1700
Data Index: 540015 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.4434. Min Act: -0.1700
Data Index: 935698 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.4121. Min Act: -0.1700
Data Index: 44582 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.2871. Min Act: -0.1700
Data Index: 3798225 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.2871. Min Act: -0.1700
Data Index: 3807007 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.1621. Min Act: -0.1700
Data Index: 4894855 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.1621. Min Act: -0.1700
Data Index: 7510264 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.1309. Min Act: -0.1700
Data Index: 409389 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0684. Min Act: -0.1700
Data Index: 8748269 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0996. Min Act: -0.1700
Data Index: 7922700 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0996. Min Act: -0.1700
Data Index: 4820225 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0684. Min Act: -0.1700
Data Index: 71919 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0996. Min Act: -0.1700
Data Index: 7744299 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0684. Min Act: -0.1700
Data Index: 6624926 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0684. Min Act: -0.1700
Data Index: 4193500 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0059. Min Act: -0.1700
Data Index: 4854226 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0371. Min Act: -0.1700
Data Index: 1852932 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0371. Min Act: -0.1700
Data Index: 8700055 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5684. Min Range: -5.5684
Max Act: 4.9746. Min Act: -0.1700
Data Index: 271731 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5684. Min Range: -5.5684
Max Act: 5.0371. Min Act: -0.1700
Data Index: 5673884 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19