Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.9515. Min Act: -0.1700
Data Index: 6889817 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8890. Min Act: -0.1700
Data Index: 2487730 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8578. Min Act: -0.1700
Data Index: 7275371 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8578. Min Act: -0.1700
Data Index: 4773457 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8578. Min Act: -0.1700
Data Index: 7196064 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8265. Min Act: -0.1700
Data Index: 7258882 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.8265. Min Act: -0.1700
Data Index: 6068052 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7640. Min Act: -0.1700
Data Index: 5844414 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7328. Min Act: -0.1700
Data Index: 3316862 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7328. Min Act: -0.1700
Data Index: 4493624 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7328. Min Act: -0.1700
Data Index: 4196418 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7015. Min Act: -0.1700
Data Index: 1078738 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7015. Min Act: -0.1700
Data Index: 5835854 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7015. Min Act: -0.1700
Data Index: 1691811 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7328. Min Act: -0.1700
Data Index: 5127517 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7328. Min Act: -0.1700
Data Index: 456064 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7015. Min Act: -0.1700
Data Index: 340147 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7328. Min Act: -0.1700
Data Index: 1537668 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.7015. Min Act: -0.1700
Data Index: 1851719 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9515. Min Range: -4.9515
Max Act: 4.6703. Min Act: -0.1700
Data Index: 4459580 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19