Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4753 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.5728. Min Act: -0.1700
Data Index: 5110797 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.2915. Min Act: -0.1700
Data Index: 674812 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.1978. Min Act: -0.1700
Data Index: 5013164 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.1978. Min Act: -0.1700
Data Index: 6478605 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.1353. Min Act: -0.1700
Data Index: 5187943 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.1040. Min Act: -0.1700
Data Index: 5358328 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.0728. Min Act: -0.1700
Data Index: 7077553 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.0415. Min Act: -0.1700
Data Index: 1285678 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.0415. Min Act: -0.1700
Data Index: 2772775 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.0415. Min Act: -0.1700
Data Index: 3385106 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.0103. Min Act: -0.1700
Data Index: 1247014 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5728. Min Range: -5.5728
Max Act: 5.0103. Min Act: -0.1700
Data Index: 3409095 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.9790. Min Act: -0.1700
Data Index: 3565008 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.9478. Min Act: -0.1700
Data Index: 4766054 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.9165. Min Act: -0.1700
Data Index: 539425 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.9165. Min Act: -0.1700
Data Index: 6605398 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.9165. Min Act: -0.1700
Data Index: 2242860 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.9165. Min Act: -0.1700
Data Index: 2855955 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.9165. Min Act: -0.1700
Data Index: 280340 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5728. Min Range: -5.5728
Max Act: 4.8540. Min Act: -0.1700
Data Index: 6059045 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19