Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2832 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.4491. Min Act: -0.1700
Data Index: 2083465 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.3866. Min Act: -0.1700
Data Index: 251434 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2929. Min Act: -0.1700
Data Index: 800695 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.3554. Min Act: -0.1700
Data Index: 6084394 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2929. Min Act: -0.1700
Data Index: 3689981 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2929. Min Act: -0.1700
Data Index: 7982314 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2616. Min Act: -0.1700
Data Index: 4885265 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2616. Min Act: -0.1700
Data Index: 5307847 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2616. Min Act: -0.1700
Data Index: 3337440 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2616. Min Act: -0.1700
Data Index: 4999169 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2303. Min Act: -0.1700
Data Index: 45034 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.2303. Min Act: -0.1700
Data Index: 2816697 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1991. Min Act: -0.1700
Data Index: 3035506 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1991. Min Act: -0.1700
Data Index: 8187688 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1991. Min Act: -0.1700
Data Index: 2907449 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1991. Min Act: -0.1700
Data Index: 4891332 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1678. Min Act: -0.1700
Data Index: 985651 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1678. Min Act: -0.1700
Data Index: 5273284 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1678. Min Act: -0.1700
Data Index: 6635540 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4491. Min Range: -4.4491
Max Act: 4.1678. Min Act: -0.1700
Data Index: 2129172 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19