Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2548. Min Range: -5.2548
Max Act: 5.2235. Min Act: -0.1700
Data Index: 8204633 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2548. Min Range: -5.2548
Max Act: 5.2548. Min Act: -0.1700
Data Index: 1710851 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2548. Min Range: -5.2548
Max Act: 5.2235. Min Act: -0.1700
Data Index: 7819829 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2548. Min Range: -5.2548
Max Act: 5.1610. Min Act: -0.1700
Data Index: 194169 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2548. Min Range: -5.2548
Max Act: 5.0673. Min Act: -0.1700
Data Index: 8533797 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2548. Min Range: -5.2548
Max Act: 5.0673. Min Act: -0.1700
Data Index: 3020584 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2548. Min Range: -5.2548
Max Act: 5.0048. Min Act: -0.1700
Data Index: 1842701 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.9735. Min Act: -0.1700
Data Index: 6683712 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.9423. Min Act: -0.1700
Data Index: 1845517 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8798. Min Act: -0.1700
Data Index: 3430864 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8798. Min Act: -0.1700
Data Index: 4196627 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8798. Min Act: -0.1700
Data Index: 4834720 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8485. Min Act: -0.1700
Data Index: 729099 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8485. Min Act: -0.1700
Data Index: 1778462 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8798. Min Act: -0.1700
Data Index: 1738577 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8173. Min Act: -0.1700
Data Index: 4834721 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.7860. Min Act: -0.1700
Data Index: 2057482 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.8173. Min Act: -0.1700
Data Index: 6137109 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.7860. Min Act: -0.1700
Data Index: 718653 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2548. Min Range: -5.2548
Max Act: 4.7860. Min Act: -0.1700
Data Index: 5067585 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19