Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 733 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.3920. Min Act: -0.1700
Data Index: 3053196 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.3608. Min Act: -0.1700
Data Index: 4327541 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2983. Min Act: -0.1700
Data Index: 6184430 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2983. Min Act: -0.1700
Data Index: 2288686 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2983. Min Act: -0.1700
Data Index: 1505852 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2670. Min Act: -0.1700
Data Index: 5689176 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2670. Min Act: -0.1700
Data Index: 6076451 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2357. Min Act: -0.1700
Data Index: 5607524 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2357. Min Act: -0.1700
Data Index: 6413244 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2045. Min Act: -0.1700
Data Index: 8770553 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2045. Min Act: -0.1700
Data Index: 2876652 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.2045. Min Act: -0.1700
Data Index: 6158276 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1732. Min Act: -0.1700
Data Index: 1479783 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1732. Min Act: -0.1700
Data Index: 4977060 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1732. Min Act: -0.1700
Data Index: 8676197 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1732. Min Act: -0.1700
Data Index: 5784778 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1420. Min Act: -0.1700
Data Index: 5219962 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1420. Min Act: -0.1700
Data Index: 4822731 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1420. Min Act: -0.1700
Data Index: 358050 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3920. Min Range: -4.3920
Max Act: 4.1420. Min Act: -0.1700
Data Index: 5007862 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19