Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.9652. Min Act: -0.1700
Data Index: 1086155 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.9027. Min Act: -0.1700
Data Index: 2043763 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.9027. Min Act: -0.1700
Data Index: 68613 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5467186 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.8402. Min Act: -0.1700
Data Index: 7958697 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.8402. Min Act: -0.1700
Data Index: 5289488 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.8089. Min Act: -0.1700
Data Index: 5332174 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7777. Min Act: -0.1700
Data Index: 551207 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7464. Min Act: -0.1700
Data Index: 4813986 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7777. Min Act: -0.1700
Data Index: 4294471 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7464. Min Act: -0.1700
Data Index: 1359653 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7152. Min Act: -0.1700
Data Index: 681284 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3720089 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7777. Min Act: -0.1700
Data Index: 5532229 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7464. Min Act: -0.1700
Data Index: 5294558 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.7464. Min Act: -0.1700
Data Index: 978221 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.6527. Min Act: -0.1700
Data Index: 6522787 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.6527. Min Act: -0.1700
Data Index: 6026283 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.6527. Min Act: -0.1700
Data Index: 5896179 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9652. Min Range: -5.9652
Max Act: 5.6527. Min Act: -0.1700
Data Index: 558761 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19