Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5022 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0224. Min Range: -4.0224
Max Act: 4.0224. Min Act: -0.1700
Data Index: 370452 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.8974. Min Act: -0.1700
Data Index: 3112617 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.8348. Min Act: -0.1700
Data Index: 8586397 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.7723. Min Act: -0.1700
Data Index: 7553541 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.8036. Min Act: -0.1700
Data Index: 251541 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.8036. Min Act: -0.1700
Data Index: 7660440 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.8036. Min Act: -0.1700
Data Index: 5338819 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.7410. Min Act: -0.1700
Data Index: 1147221 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.7097. Min Act: -0.1700
Data Index: 2605958 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.7097. Min Act: -0.1700
Data Index: 267890 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.6784. Min Act: -0.1700
Data Index: 2266469 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.7097. Min Act: -0.1700
Data Index: 4817750 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.7097. Min Act: -0.1700
Data Index: 8525408 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.6784. Min Act: -0.1700
Data Index: 755537 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.6784. Min Act: -0.1700
Data Index: 3714784 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.7097. Min Act: -0.1700
Data Index: 6411221 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.6784. Min Act: -0.1700
Data Index: 235959 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.6784. Min Act: -0.1700
Data Index: 3137653 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.6784. Min Act: -0.1700
Data Index: 1432420 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0224. Min Range: -4.0224
Max Act: 3.6784. Min Act: -0.1700
Data Index: 431661 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19