Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1058. Min Range: -8.1058
Max Act: 8.1058. Min Act: -0.1700
Data Index: 4982301 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.9808. Min Act: -0.1700
Data Index: 3662810 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.7620. Min Act: -0.1700
Data Index: 7191584 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.7308. Min Act: -0.1700
Data Index: 3459394 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.7620. Min Act: -0.1700
Data Index: 2625459 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.6370. Min Act: -0.1700
Data Index: 7848348 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.5433. Min Act: -0.1700
Data Index: 3309579 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.4808. Min Act: -0.1700
Data Index: 2766837 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.4808. Min Act: -0.1700
Data Index: 2658682 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.3558. Min Act: -0.1700
Data Index: 6248093 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.3245. Min Act: -0.1700
Data Index: 4385555 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.4183. Min Act: -0.1700
Data Index: 7745456 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.3558. Min Act: -0.1700
Data Index: 5305455 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.3245. Min Act: -0.1700
Data Index: 5938696 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.2933. Min Act: -0.1700
Data Index: 6002286 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.2933. Min Act: -0.1700
Data Index: 4178856 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.2933. Min Act: -0.1700
Data Index: 5185095 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.2620. Min Act: -0.1700
Data Index: 6604071 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.2308. Min Act: -0.1700
Data Index: 5584936 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1058. Min Range: -8.1058
Max Act: 7.2308. Min Act: -0.1700
Data Index: 3763855 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19