Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2473 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.5702. Min Act: -0.1700
Data Index: 2017480 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4825. Min Act: -0.1697
Data Index: 3914637 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.5001. Min Act: -0.1700
Data Index: 3913419 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4825. Min Act: -0.1689
Data Index: 4373057 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4913. Min Act: -0.1692
Data Index: 4487167 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4649. Min Act: -0.1699
Data Index: 6515498 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4562. Min Act: -0.1697
Data Index: 8507618 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4474. Min Act: -0.1695
Data Index: 264342 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4298. Min Act: -0.1699
Data Index: 5535388 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4033. Min Act: -0.1690
Data Index: 2634984 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4121. Min Act: -0.1700
Data Index: 1177472 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4121. Min Act: -0.1699
Data Index: 3343792 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.4033. Min Act: -0.1695
Data Index: 4626958 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.3769. Min Act: -0.1698
Data Index: 4127423 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.3769. Min Act: -0.1698
Data Index: 801758 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.3681. Min Act: -0.1700
Data Index: 2565456 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.3769. Min Act: -0.1700
Data Index: 2984989 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.3681. Min Act: -0.1699
Data Index: 2496199 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.3769. Min Act: -0.1700
Data Index: 4133960 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5702. Min Range: -1.5702
Max Act: 1.3769. Min Act: -0.1700
Data Index: 6445836 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19