Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.4313. Min Act: -0.1700
Data Index: 3724297 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.2438. Min Act: -0.1700
Data Index: 1566731 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.1813. Min Act: -0.1700
Data Index: 6327088 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.1500. Min Act: -0.1700
Data Index: 8475185 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.1500. Min Act: -0.1700
Data Index: 3656946 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0563. Min Act: -0.1700
Data Index: 376929 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0563. Min Act: -0.1700
Data Index: 1282133 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0563. Min Act: -0.1700
Data Index: 127120 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0563. Min Act: -0.1700
Data Index: 4193777 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4313. Min Range: -5.4313
Max Act: 4.9938. Min Act: -0.1700
Data Index: 6258814 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0563. Min Act: -0.1700
Data Index: 462095 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0250. Min Act: -0.1700
Data Index: 1852470 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0250. Min Act: -0.1700
Data Index: 6666003 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4313. Min Range: -5.4313
Max Act: 5.0250. Min Act: -0.1700
Data Index: 5841639 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4313. Min Range: -5.4313
Max Act: 4.9938. Min Act: -0.1700
Data Index: 2278693 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4313. Min Range: -5.4313
Max Act: 4.9938. Min Act: -0.1700
Data Index: 7463931 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4313. Min Range: -5.4313
Max Act: 4.9938. Min Act: -0.1700
Data Index: 7064967 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4313. Min Range: -5.4313
Max Act: 4.9938. Min Act: -0.1700
Data Index: 1437948 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4313. Min Range: -5.4313
Max Act: 4.9938. Min Act: -0.1700
Data Index: 2473743 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4313. Min Range: -5.4313
Max Act: 4.9938. Min Act: -0.1700
Data Index: 2171028 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19