Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4016 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.3642. Min Act: -0.1700
Data Index: 7242851 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.3329. Min Act: -0.1700
Data Index: 6924291 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.3329. Min Act: -0.1700
Data Index: 2037202 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.3329. Min Act: -0.1700
Data Index: 8231149 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.3017. Min Act: -0.1698
Data Index: 7550847 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.2392. Min Act: -0.1700
Data Index: 6614488 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.2392. Min Act: -0.1700
Data Index: 2226794 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.2392. Min Act: -0.1699
Data Index: 4141644 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.2079. Min Act: -0.1700
Data Index: 5024081 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1454. Min Act: -0.1700
Data Index: 7377753 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1767. Min Act: -0.1700
Data Index: 8671634 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1767. Min Act: -0.1700
Data Index: 4505530 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1767. Min Act: -0.1700
Data Index: 7082646 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1767. Min Act: -0.1700
Data Index: 7779906 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.2079. Min Act: -0.1700
Data Index: 1816156 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.2079. Min Act: -0.1700
Data Index: 7627476 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1454. Min Act: -0.1700
Data Index: 2233206 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1142. Min Act: -0.1700
Data Index: 479762 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1454. Min Act: -0.1700
Data Index: 7054156 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3642. Min Range: -5.3642
Max Act: 5.1454. Min Act: -0.1700
Data Index: 6978720 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19