Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.4821. Min Act: -0.1700
Data Index: 1223768 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.4821. Min Act: -0.1700
Data Index: 5790327 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.4196. Min Act: -0.1700
Data Index: 8638652 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.3883. Min Act: -0.1700
Data Index: 3742386 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.3571. Min Act: -0.1700
Data Index: 16899 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.2633. Min Act: -0.1700
Data Index: 5308449 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.2633. Min Act: -0.1700
Data Index: 1444875 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.2321. Min Act: -0.1700
Data Index: 3304884 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.2633. Min Act: -0.1700
Data Index: 2636433 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.2321. Min Act: -0.1700
Data Index: 2939601 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.2321. Min Act: -0.1700
Data Index: 4771825 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.1696. Min Act: -0.1700
Data Index: 1990477 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.1383. Min Act: -0.1700
Data Index: 1596575 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.2008. Min Act: -0.1700
Data Index: 2324509 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.1383. Min Act: -0.1700
Data Index: 6644742 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.1383. Min Act: -0.1700
Data Index: 848300 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.1071. Min Act: -0.1700
Data Index: 6006866 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4821. Min Range: -5.4821
Max Act: 5.0446. Min Act: -0.1700
Data Index: 1937738 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4821. Min Range: -5.4821
Max Act: 4.9821. Min Act: -0.1700
Data Index: 5445762 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4821. Min Range: -5.4821
Max Act: 4.9821. Min Act: -0.1700
Data Index: 4939386 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19