Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.6239. Min Act: -0.1700
Data Index: 819093 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.4298. Min Act: -0.1700
Data Index: 286067 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3972. Min Act: -0.1700
Data Index: 3026350 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.4135. Min Act: -0.1700
Data Index: 5317433 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3972. Min Act: -0.1700
Data Index: 4094434 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3809. Min Act: -0.1700
Data Index: 3088156 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3809. Min Act: -0.1700
Data Index: 3399378 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3809. Min Act: -0.1700
Data Index: 2828208 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3482. Min Act: -0.1700
Data Index: 988049 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3645. Min Act: -0.1700
Data Index: 799973 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3482. Min Act: -0.1700
Data Index: 5292063 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3645. Min Act: -0.1700
Data Index: 513264 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3645. Min Act: -0.1700
Data Index: 21949 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3482. Min Act: -0.1700
Data Index: 656057 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3482. Min Act: -0.1700
Data Index: 8139675 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3318. Min Act: -0.1700
Data Index: 4601540 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3318. Min Act: -0.1700
Data Index: 36486 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3318. Min Act: -0.1700
Data Index: 6872342 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3318. Min Act: -0.1700
Data Index: 4149359 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6239. Min Range: -2.6239
Max Act: 2.3318. Min Act: -0.1700
Data Index: 7482369 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19