Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.4228. Min Act: -0.1700
Data Index: 8649663 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.3914. Min Act: -0.1700
Data Index: 3127282 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.3758. Min Act: -0.1700
Data Index: 2430148 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.3601. Min Act: -0.1700
Data Index: 825708 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.3130. Min Act: -0.1700
Data Index: 6191405 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2816. Min Act: -0.1700
Data Index: 3815028 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2502. Min Act: -0.1700
Data Index: 6580586 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2345. Min Act: -0.1700
Data Index: 6018633 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2345. Min Act: -0.1700
Data Index: 607887 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2502. Min Act: -0.1700
Data Index: 4103931 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2187. Min Act: -0.1700
Data Index: 5268066 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2187. Min Act: -0.1700
Data Index: 3658753 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2502. Min Act: -0.1700
Data Index: 8649664 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2345. Min Act: -0.1700
Data Index: 4236030 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2187. Min Act: -0.1700
Data Index: 398871 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2345. Min Act: -0.1700
Data Index: 1461409 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2187. Min Act: -0.1700
Data Index: 2736288 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.1873. Min Act: -0.1700
Data Index: 6600718 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.2187. Min Act: -0.1700
Data Index: 8286982 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4228. Min Range: -3.4228
Max Act: 3.1873. Min Act: -0.1700
Data Index: 2995606 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19