Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5345 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0208. Min Range: -8.0208
Max Act: 8.0208. Min Act: -0.1700
Data Index: 633549 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.9271. Min Act: -0.1700
Data Index: 8170115 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.6771. Min Act: -0.1700
Data Index: 1188158 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.6146. Min Act: -0.1700
Data Index: 5272629 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.5521. Min Act: -0.1700
Data Index: 8823167 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.4896. Min Act: -0.1700
Data Index: 7300750 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.4271. Min Act: -0.1700
Data Index: 123070 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3958. Min Act: -0.1700
Data Index: 925033 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3958. Min Act: -0.1700
Data Index: 4414771 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3646. Min Act: -0.1700
Data Index: 448544 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3333. Min Act: -0.1700
Data Index: 7770600 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3333. Min Act: -0.1700
Data Index: 20483 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3021. Min Act: -0.1700
Data Index: 8373503 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3021. Min Act: -0.1700
Data Index: 2683074 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3333. Min Act: -0.1700
Data Index: 2577339 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.3021. Min Act: -0.1700
Data Index: 926567 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.2708. Min Act: -0.1700
Data Index: 4230737 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.2708. Min Act: -0.1700
Data Index: 8173157 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.2396. Min Act: -0.1700
Data Index: 6887259 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0208. Min Range: -8.0208
Max Act: 7.2396. Min Act: -0.1700
Data Index: 2453077 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19