Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1645. Min Range: -5.1645
Max Act: 5.1645. Min Act: -0.1700
Data Index: 704812 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.9770. Min Act: -0.1700
Data Index: 3966796 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.9145. Min Act: -0.1700
Data Index: 3510781 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.9458. Min Act: -0.1700
Data Index: 7231160 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.8208. Min Act: -0.1700
Data Index: 8373210 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.7895. Min Act: -0.1700
Data Index: 6507521 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6645. Min Act: -0.1700
Data Index: 8660880 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6958. Min Act: -0.1700
Data Index: 3618357 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6645. Min Act: -0.1700
Data Index: 36490 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6333. Min Act: -0.1700
Data Index: 923384 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6645. Min Act: -0.1700
Data Index: 4589703 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6333. Min Act: -0.1700
Data Index: 8046020 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6958. Min Act: -0.1700
Data Index: 1294014 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6645. Min Act: -0.1700
Data Index: 5162501 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6333. Min Act: -0.1700
Data Index: 606667 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6333. Min Act: -0.1700
Data Index: 3954436 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6333. Min Act: -0.1700
Data Index: 6689818 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6020. Min Act: -0.1700
Data Index: 3580836 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6333. Min Act: -0.1700
Data Index: 843010 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1645. Min Range: -5.1645
Max Act: 4.6020. Min Act: -0.1700
Data Index: 4101770 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19