Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.6499. Min Act: -0.1699
Data Index: 6943773 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.6339. Min Act: -0.1696
Data Index: 1161881 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.6419. Min Act: -0.1700
Data Index: 366543 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.6339. Min Act: -0.1700
Data Index: 6268800 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.6180. Min Act: -0.1700
Data Index: 8049404 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.6100. Min Act: -0.1699
Data Index: 440312 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5709. Min Act: -0.1700
Data Index: 8792691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5554. Min Act: -0.1697
Data Index: 2596168 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5554. Min Act: -0.1685
Data Index: 690611 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5554. Min Act: -0.1695
Data Index: 2541387 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5323. Min Act: -0.1686
Data Index: 7005575 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5400. Min Act: -0.1700
Data Index: 2349434 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5323. Min Act: -0.1700
Data Index: 1687388 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5323. Min Act: -0.1700
Data Index: 5041022 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5171. Min Act: -0.1700
Data Index: 2988870 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5247. Min Act: -0.1698
Data Index: 1056244 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5247. Min Act: -0.1700
Data Index: 1650714 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5171. Min Act: -0.1700
Data Index: 273225 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5171. Min Act: -0.1700
Data Index: 2818813 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6499. Min Range: -0.6499
Max Act: 0.5247. Min Act: -0.1698
Data Index: 3515974 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19