Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.5885. Min Act: -0.1700
Data Index: 2992760 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.5416. Min Act: -0.1700
Data Index: 932420 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.5259. Min Act: -0.1700
Data Index: 7569241 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.5103. Min Act: -0.1700
Data Index: 8086487 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.5103. Min Act: -0.1700
Data Index: 2092310 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3606112 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4946. Min Act: -0.1700
Data Index: 1634184 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4946. Min Act: -0.1700
Data Index: 2101872 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4946. Min Act: -0.1700
Data Index: 7405925 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4789. Min Act: -0.1700
Data Index: 226716 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4789. Min Act: -0.1700
Data Index: 8685386 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4633. Min Act: -0.1700
Data Index: 5342092 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4633. Min Act: -0.1700
Data Index: 314438 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4476. Min Act: -0.1700
Data Index: 7352489 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4633. Min Act: -0.1700
Data Index: 8788415 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4476. Min Act: -0.1700
Data Index: 5990510 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4163. Min Act: -0.1700
Data Index: 4820955 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4163. Min Act: -0.1700
Data Index: 1188863 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4006. Min Act: -0.1700
Data Index: 7075281 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5885. Min Range: -3.5885
Max Act: 3.4163. Min Act: -0.1700
Data Index: 2962279 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19