Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.7868. Min Act: -0.1700
Data Index: 7557085 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.6305. Min Act: -0.1700
Data Index: 1937547 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5993. Min Act: -0.1700
Data Index: 4068112 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5993. Min Act: -0.1700
Data Index: 5966359 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5680. Min Act: -0.1700
Data Index: 5697839 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5993. Min Act: -0.1700
Data Index: 4819387 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5680. Min Act: -0.1700
Data Index: 4819375 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5993. Min Act: -0.1700
Data Index: 1252767 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 4819376 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5680. Min Act: -0.1700
Data Index: 1064275 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 5992990 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 6133214 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 8802319 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 1664169 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 8802318 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1699
Data Index: 1394508 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 1435830 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 8297057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 1944312 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.4743. Min Act: -0.1700
Data Index: 288976 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19