Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4505 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1233. Min Range: -1.1233
Max Act: 1.1233. Min Act: -0.1700
Data Index: 6602380 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1233. Min Range: -1.1233
Max Act: 1.0708. Min Act: -0.1694
Data Index: 961416 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.9320. Min Act: -0.1689
Data Index: 8725519 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.8891. Min Act: -0.1691
Data Index: 3013770 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.8721. Min Act: -0.1695
Data Index: 330367 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.8381. Min Act: -0.1671
Data Index: 3088779 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.8128. Min Act: -0.1687
Data Index: 6647403 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7877. Min Act: -0.1691
Data Index: 3144145 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7710. Min Act: -0.1680
Data Index: 4752203 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7710. Min Act: -0.1700
Data Index: 3944258 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7627. Min Act: -0.1700
Data Index: 1525606 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7544. Min Act: -0.1699
Data Index: 8586716 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7627. Min Act: -0.1700
Data Index: 3669271 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7378. Min Act: -0.1700
Data Index: 7129259 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7378. Min Act: -0.1695
Data Index: 4499204 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7461. Min Act: -0.1699
Data Index: 6023272 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7544. Min Act: -0.1700
Data Index: 3621948 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7378. Min Act: -0.1674
Data Index: 6395525 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7461. Min Act: -0.1699
Data Index: 6250962 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1233. Min Range: -1.1233
Max Act: 0.7296. Min Act: -0.1700
Data Index: 6395526 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19