Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3003. Min Range: -5.3003
Max Act: 5.3003. Min Act: -0.1700
Data Index: 2704634 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3003. Min Range: -5.3003
Max Act: 5.0503. Min Act: -0.1700
Data Index: 8542165 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.9566. Min Act: -0.1700
Data Index: 681320 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.9566. Min Act: -0.1700
Data Index: 4236931 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.9253. Min Act: -0.1700
Data Index: 1945085 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.9253. Min Act: -0.1700
Data Index: 5311450 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.9566. Min Act: -0.1700
Data Index: 863785 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8941. Min Act: -0.1700
Data Index: 5088344 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8941. Min Act: -0.1700
Data Index: 391915 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8941. Min Act: -0.1700
Data Index: 4615265 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8628. Min Act: -0.1700
Data Index: 1801607 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8628. Min Act: -0.1700
Data Index: 1572942 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8003. Min Act: -0.1700
Data Index: 1736448 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8316. Min Act: -0.1700
Data Index: 2976331 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.8316. Min Act: -0.1700
Data Index: 7727851 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.7691. Min Act: -0.1700
Data Index: 4834532 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.7691. Min Act: -0.1700
Data Index: 2001253 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.7378. Min Act: -0.1700
Data Index: 7179030 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.7378. Min Act: -0.1700
Data Index: 2218817 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3003. Min Range: -5.3003
Max Act: 4.7378. Min Act: -0.1700
Data Index: 3240570 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19