Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3738. Min Range: -7.3738
Max Act: 7.3738. Min Act: -0.1700
Data Index: 6812872 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3738. Min Range: -7.3738
Max Act: 7.1550. Min Act: -0.1700
Data Index: 4974261 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.9363. Min Act: -0.1700
Data Index: 8681218 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.9050. Min Act: -0.1700
Data Index: 8231160 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.8113. Min Act: -0.1700
Data Index: 287593 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.8113. Min Act: -0.1700
Data Index: 4213642 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.8113. Min Act: -0.1700
Data Index: 6225825 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.7800. Min Act: -0.1700
Data Index: 6886010 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.7800. Min Act: -0.1700
Data Index: 2024650 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6855173 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.7488. Min Act: -0.1700
Data Index: 7868082 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.6863. Min Act: -0.1700
Data Index: 1332128 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.6863. Min Act: -0.1700
Data Index: 2532904 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.6550. Min Act: -0.1700
Data Index: 2556256 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.6863. Min Act: -0.1700
Data Index: 3409856 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.6238. Min Act: -0.1700
Data Index: 3338117 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.5925. Min Act: -0.1700
Data Index: 1701020 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.5925. Min Act: -0.1700
Data Index: 6850520 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.5613. Min Act: -0.1700
Data Index: 3066639 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3738. Min Range: -7.3738
Max Act: 6.5613. Min Act: -0.1700
Data Index: 2603682 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19