Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 755 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.7425. Min Act: -0.1700
Data Index: 6616472 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.5078. Min Act: -0.1700
Data Index: 7654241 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.5235. Min Act: -0.1700
Data Index: 97695 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.4608. Min Act: -0.1700
Data Index: 734483 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.3981. Min Act: -0.1700
Data Index: 1090070 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.2569. Min Act: -0.1700
Data Index: 1717450 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.2254. Min Act: -0.1700
Data Index: 4521622 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.2412. Min Act: -0.1700
Data Index: 4709846 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.1940. Min Act: -0.1700
Data Index: 97692 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.1153. Min Act: -0.1700
Data Index: 3086701 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.0995. Min Act: -0.1700
Data Index: 8710945 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.0838. Min Act: -0.1700
Data Index: 8075399 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.0680. Min Act: -0.1700
Data Index: 3869771 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.0522. Min Act: -0.1700
Data Index: 3938826 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.0364. Min Act: -0.1700
Data Index: 5599334 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7425. Min Range: -3.7425
Max Act: 2.9732. Min Act: -0.1700
Data Index: 6987303 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.0207. Min Act: -0.1700
Data Index: 1443506 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7425. Min Range: -3.7425
Max Act: 3.0049. Min Act: -0.1700
Data Index: 6664953 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7425. Min Range: -3.7425
Max Act: 2.9890. Min Act: -0.1700
Data Index: 2944820 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7425. Min Range: -3.7425
Max Act: 2.9890. Min Act: -0.1700
Data Index: 3346182 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19