Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1542. Min Range: -8.1542
Max Act: 8.1542. Min Act: -0.1700
Data Index: 699169 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.6230. Min Act: -0.1700
Data Index: 6179556 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.6230. Min Act: -0.1700
Data Index: 6143982 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.5605. Min Act: -0.1700
Data Index: 2963089 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.5605. Min Act: -0.1700
Data Index: 6868999 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.4667. Min Act: -0.1700
Data Index: 4688988 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.4980. Min Act: -0.1700
Data Index: 6179554 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.4667. Min Act: -0.1700
Data Index: 2819518 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.4355. Min Act: -0.1700
Data Index: 3309687 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.4355. Min Act: -0.1700
Data Index: 1778987 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3730. Min Act: -0.1700
Data Index: 5710400 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3730. Min Act: -0.1700
Data Index: 6876668 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.4042. Min Act: -0.1700
Data Index: 7698123 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3417. Min Act: -0.1700
Data Index: 2749915 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3417. Min Act: -0.1700
Data Index: 4762401 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3417. Min Act: -0.1700
Data Index: 2963091 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3105. Min Act: -0.1700
Data Index: 4220622 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3105. Min Act: -0.1700
Data Index: 7272063 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.3105. Min Act: -0.1700
Data Index: 6838585 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1542. Min Range: -8.1542
Max Act: 7.2792. Min Act: -0.1700
Data Index: 7830232 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19