Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.5776. Min Act: -0.1700
Data Index: 3732266 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.4053. Min Act: -0.1700
Data Index: 7069339 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.3739. Min Act: -0.1700
Data Index: 4461630 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.3582. Min Act: -0.1700
Data Index: 3344839 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.3425. Min Act: -0.1700
Data Index: 3488801 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.3425. Min Act: -0.1700
Data Index: 639874 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.3112. Min Act: -0.1700
Data Index: 3654075 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2955. Min Act: -0.1700
Data Index: 6344013 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.3112. Min Act: -0.1700
Data Index: 8476816 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2798. Min Act: -0.1700
Data Index: 4302454 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2955. Min Act: -0.1700
Data Index: 7480101 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2640. Min Act: -0.1700
Data Index: 6685594 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2640. Min Act: -0.1700
Data Index: 2007848 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2326. Min Act: -0.1700
Data Index: 8109204 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2326. Min Act: -0.1700
Data Index: 4437203 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2169. Min Act: -0.1700
Data Index: 533146 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2169. Min Act: -0.1700
Data Index: 7347570 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.2012. Min Act: -0.1700
Data Index: 971802 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.1855. Min Act: -0.1700
Data Index: 7344473 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5776. Min Range: -3.5776
Max Act: 3.1855. Min Act: -0.1700
Data Index: 2892096 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19