Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4197 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4298. Min Range: -6.4298
Max Act: 6.4298. Min Act: -0.1700
Data Index: 1254828 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4298. Min Range: -6.4298
Max Act: 6.2110. Min Act: -0.1700
Data Index: 5273291 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.8985. Min Act: -0.1700
Data Index: 2590892 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.8673. Min Act: -0.1700
Data Index: 1545727 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.8360. Min Act: -0.1700
Data Index: 2571586 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.7735. Min Act: -0.1700
Data Index: 172155 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.7110. Min Act: -0.1700
Data Index: 2973103 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.6798. Min Act: -0.1700
Data Index: 2093624 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.6485. Min Act: -0.1700
Data Index: 4937390 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.6485. Min Act: -0.1700
Data Index: 7798618 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4651057 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5860. Min Act: -0.1700
Data Index: 920120 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4965735 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5860. Min Act: -0.1700
Data Index: 3636810 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5860. Min Act: -0.1700
Data Index: 341072 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5860. Min Act: -0.1700
Data Index: 7092127 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5548. Min Act: -0.1700
Data Index: 3678088 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5235. Min Act: -0.1700
Data Index: 2021329 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5235. Min Act: -0.1700
Data Index: 3714540 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4298. Min Range: -6.4298
Max Act: 5.5235. Min Act: -0.1700
Data Index: 3624142 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19