Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4057 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2943. Min Act: -0.1700
Data Index: 3810988 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.3257. Min Act: -0.1700
Data Index: 3263554 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.3100. Min Act: -0.1700
Data Index: 5670059 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.3100. Min Act: -0.1700
Data Index: 8231563 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2786. Min Act: -0.1700
Data Index: 2571548 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2943. Min Act: -0.1700
Data Index: 8201552 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2629. Min Act: -0.1700
Data Index: 392739 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2629. Min Act: -0.1700
Data Index: 4901460 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2472. Min Act: -0.1700
Data Index: 1564639 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2472. Min Act: -0.1700
Data Index: 6429996 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2000. Min Act: -0.1700
Data Index: 8013952 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1843. Min Act: -0.1700
Data Index: 140938 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.2000. Min Act: -0.1700
Data Index: 4808699 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1686. Min Act: -0.1700
Data Index: 1595026 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1528. Min Act: -0.1700
Data Index: 8674148 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1528. Min Act: -0.1700
Data Index: 7865895 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1686. Min Act: -0.1700
Data Index: 1106145 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1528. Min Act: -0.1700
Data Index: 8384216 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1528. Min Act: -0.1700
Data Index: 3127386 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3257. Min Range: -3.3257
Max Act: 3.1686. Min Act: -0.1700
Data Index: 558181 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19