Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 847 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.9371. Min Act: -0.1700
Data Index: 1950017 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.9371. Min Act: -0.1700
Data Index: 3982972 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.9058. Min Act: -0.1700
Data Index: 4502979 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1241367 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.8433. Min Act: -0.1700
Data Index: 7856233 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.8121. Min Act: -0.1700
Data Index: 7345166 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.7808. Min Act: -0.1700
Data Index: 2722539 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.7496. Min Act: -0.1700
Data Index: 1241375 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.7496. Min Act: -0.1700
Data Index: 1301115 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.7496. Min Act: -0.1700
Data Index: 3475125 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.7183. Min Act: -0.1700
Data Index: 2973070 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.6871. Min Act: -0.1700
Data Index: 4953936 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.6871. Min Act: -0.1700
Data Index: 4953932 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.6558. Min Act: -0.1700
Data Index: 4953938 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.6871. Min Act: -0.1700
Data Index: 8526709 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.6246. Min Act: -0.1700
Data Index: 2902237 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.5933. Min Act: -0.1700
Data Index: 1466087 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.5621. Min Act: -0.1700
Data Index: 5073490 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.6246. Min Act: -0.1700
Data Index: 7251014 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9371. Min Range: -5.9371
Max Act: 5.5933. Min Act: -0.1700
Data Index: 6963342 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19