Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.4756. Min Act: -0.1700
Data Index: 3401074 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.3973. Min Act: -0.1700
Data Index: 5450904 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.4129. Min Act: -0.1700
Data Index: 8722035 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.3188. Min Act: -0.1700
Data Index: 4903981 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2874. Min Act: -0.1700
Data Index: 3599212 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2874. Min Act: -0.1700
Data Index: 1362623 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2874. Min Act: -0.1700
Data Index: 8767346 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2717. Min Act: -0.1700
Data Index: 5310066 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2560. Min Act: -0.1700
Data Index: 3779442 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2246. Min Act: -0.1700
Data Index: 901007 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2246. Min Act: -0.1700
Data Index: 94986 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2089. Min Act: -0.1700
Data Index: 8125480 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2089. Min Act: -0.1700
Data Index: 4903980 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2089. Min Act: -0.1700
Data Index: 5361019 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.1774. Min Act: -0.1700
Data Index: 1771064 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2089. Min Act: -0.1700
Data Index: 248777 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.2089. Min Act: -0.1700
Data Index: 5411859 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.1617. Min Act: -0.1700
Data Index: 7220536 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.1617. Min Act: -0.1700
Data Index: 2915529 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4756. Min Range: -3.4756
Max Act: 3.1617. Min Act: -0.1700
Data Index: 4755766 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19