Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 963 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.1343. Min Act: -0.1700
Data Index: 3348273 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.1031. Min Act: -0.1700
Data Index: 8311418 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.1031. Min Act: -0.1700
Data Index: 7652041 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.1343. Min Act: -0.1700
Data Index: 6417803 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.1031. Min Act: -0.1700
Data Index: 5985634 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.0718. Min Act: -0.1700
Data Index: 2728868 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.0405. Min Act: -0.1700
Data Index: 2363497 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.0405. Min Act: -0.1700
Data Index: 5275574 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9780. Min Act: -0.1700
Data Index: 2848902 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.0405. Min Act: -0.1700
Data Index: 8438827 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.0093. Min Act: -0.1700
Data Index: 1914220 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9780. Min Act: -0.1700
Data Index: 4760955 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9780. Min Act: -0.1700
Data Index: 3415482 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9468. Min Act: -0.1700
Data Index: 1070048 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9468. Min Act: -0.1700
Data Index: 6903869 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9780. Min Act: -0.1700
Data Index: 3884037 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1343. Min Range: -4.1343
Max Act: 4.0093. Min Act: -0.1700
Data Index: 7719225 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9468. Min Act: -0.1700
Data Index: 8059978 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9624. Min Act: -0.1700
Data Index: 7491956 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1343. Min Range: -4.1343
Max Act: 3.9468. Min Act: -0.1700
Data Index: 2727749 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19