Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0445. Min Range: -2.0445
Max Act: 2.0445. Min Act: -0.1700
Data Index: 4973810 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0445. Min Range: -2.0445
Max Act: 2.0277. Min Act: -0.1700
Data Index: 2447235 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0445. Min Range: -2.0445
Max Act: 2.0277. Min Act: -0.1700
Data Index: 6903815 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9939. Min Act: -0.1700
Data Index: 7919754 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9600. Min Act: -0.1697
Data Index: 3302989 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9770. Min Act: -0.1700
Data Index: 4440497 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9600. Min Act: -0.1700
Data Index: 4440496 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9600. Min Act: -0.1700
Data Index: 528621 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9600. Min Act: -0.1700
Data Index: 2560896 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9430. Min Act: -0.1700
Data Index: 4440495 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9260. Min Act: -0.1700
Data Index: 651470 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9430. Min Act: -0.1700
Data Index: 3710578 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9430. Min Act: -0.1700
Data Index: 922831 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9430. Min Act: -0.1700
Data Index: 4973809 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9430. Min Act: -0.1700
Data Index: 2892593 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9430. Min Act: -0.1700
Data Index: 8826298 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9260. Min Act: -0.1603
Data Index: 4440498 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9260. Min Act: -0.1700
Data Index: 4351714 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9260. Min Act: -0.1700
Data Index: 3251673 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0445. Min Range: -2.0445
Max Act: 1.9260. Min Act: -0.1700
Data Index: 8070620 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19