Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2335 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.5352. Min Act: -0.1700
Data Index: 4218697 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4414. Min Act: -0.1700
Data Index: 5838950 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.4102. Min Act: -0.1700
Data Index: 7272160 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3789. Min Act: -0.1700
Data Index: 4089447 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.3477. Min Act: -0.1700
Data Index: 6455346 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.2852. Min Act: -0.1700
Data Index: 6344133 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.2539. Min Act: -0.1700
Data Index: 2816368 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.1914. Min Act: -0.1700
Data Index: 4458489 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.1914. Min Act: -0.1700
Data Index: 4201397 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.1914. Min Act: -0.1700
Data Index: 160896 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.1602. Min Act: -0.1700
Data Index: 2104921 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.1602. Min Act: -0.1700
Data Index: 7193246 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0352. Min Act: -0.1700
Data Index: 4169729 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0664. Min Act: -0.1700
Data Index: 6154123 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0977. Min Act: -0.1700
Data Index: 4664629 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0352. Min Act: -0.1700
Data Index: 207658 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0664. Min Act: -0.1700
Data Index: 8589259 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0039. Min Act: -0.1700
Data Index: 1444613 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0039. Min Act: -0.1700
Data Index: 248854 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5352. Min Range: -6.5352
Max Act: 6.0039. Min Act: -0.1700
Data Index: 2237803 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19