Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 534 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.3708. Min Act: -0.1700
Data Index: 1718070 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.2770. Min Act: -0.1700
Data Index: 7938427 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.2145. Min Act: -0.1700
Data Index: 1080981 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.1833. Min Act: -0.1700
Data Index: 3701879 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.0895. Min Act: -0.1700
Data Index: 5677266 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.1208. Min Act: -0.1700
Data Index: 6061213 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.0895. Min Act: -0.1700
Data Index: 6071799 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.0583. Min Act: -0.1700
Data Index: 562395 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.0583. Min Act: -0.1700
Data Index: 6804606 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.0270. Min Act: -0.1700
Data Index: 5662294 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.0270. Min Act: -0.1700
Data Index: 909580 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3708. Min Range: -5.3708
Max Act: 5.0270. Min Act: -0.1700
Data Index: 7046074 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.9958. Min Act: -0.1700
Data Index: 5795438 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.9333. Min Act: -0.1700
Data Index: 6657198 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.9645. Min Act: -0.1700
Data Index: 516200 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.9333. Min Act: -0.1700
Data Index: 157411 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.8708. Min Act: -0.1700
Data Index: 71727 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.9020. Min Act: -0.1700
Data Index: 5054050 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.8708. Min Act: -0.1700
Data Index: 6581775 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3708. Min Range: -5.3708
Max Act: 4.9020. Min Act: -0.1700
Data Index: 7346467 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19