Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2578 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.9371. Min Act: -0.1700
Data Index: 5289317 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.9058. Min Act: -0.1700
Data Index: 4962711 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.8433. Min Act: -0.1700
Data Index: 4248534 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.7808. Min Act: -0.1700
Data Index: 5268219 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.7808. Min Act: -0.1700
Data Index: 8826510 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.7496. Min Act: -0.1700
Data Index: 3127386 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.7183. Min Act: -0.1700
Data Index: 7057619 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.7808. Min Act: -0.1700
Data Index: 3357614 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6785672 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.7183. Min Act: -0.1700
Data Index: 4745202 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6871. Min Act: -0.1700
Data Index: 2155801 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6558. Min Act: -0.1700
Data Index: 5817374 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6871. Min Act: -0.1700
Data Index: 7701568 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6871. Min Act: -0.1700
Data Index: 4193270 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6871. Min Act: -0.1700
Data Index: 8559923 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6558. Min Act: -0.1700
Data Index: 5985773 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6871. Min Act: -0.1700
Data Index: 8534023 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6558. Min Act: -0.1700
Data Index: 4528390 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6558. Min Act: -0.1700
Data Index: 455511 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9371. Min Range: -4.9371
Max Act: 4.6871. Min Act: -0.1700
Data Index: 5350146 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19