Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3936 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3627. Min Range: -8.3627
Max Act: 8.3627. Min Act: -0.1700
Data Index: 112268 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3627. Min Range: -8.3627
Max Act: 8.3002. Min Act: -0.1700
Data Index: 258422 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.8627. Min Act: -0.1700
Data Index: 544174 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.8627. Min Act: -0.1700
Data Index: 487502 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.7377. Min Act: -0.1700
Data Index: 5639637 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.6752. Min Act: -0.1700
Data Index: 6453023 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.6127. Min Act: -0.1700
Data Index: 8486266 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.5502. Min Act: -0.1700
Data Index: 7637331 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.5502. Min Act: -0.1700
Data Index: 4914342 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.5189. Min Act: -0.1700
Data Index: 76191 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.5189. Min Act: -0.1700
Data Index: 6886568 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.4877. Min Act: -0.1700
Data Index: 3645611 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.4252. Min Act: -0.1700
Data Index: 8411602 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.3939. Min Act: -0.1700
Data Index: 6235898 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.3939. Min Act: -0.1700
Data Index: 5500051 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.3627. Min Act: -0.1700
Data Index: 6919050 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.3627. Min Act: -0.1700
Data Index: 6545778 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.3627. Min Act: -0.1700
Data Index: 174690 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.3627. Min Act: -0.1700
Data Index: 103105 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3627. Min Range: -8.3627
Max Act: 7.3314. Min Act: -0.1700
Data Index: 5269751 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19