Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.1891. Min Act: -0.1700
Data Index: 3369134 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0953. Min Act: -0.1700
Data Index: 1474933 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0953. Min Act: -0.1700
Data Index: 7426852 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0328. Min Act: -0.1700
Data Index: 7228581 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0328. Min Act: -0.1700
Data Index: 5100628 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0328. Min Act: -0.1700
Data Index: 5116652 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0328. Min Act: -0.1700
Data Index: 3603201 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0328. Min Act: -0.1700
Data Index: 7956571 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1891. Min Range: -4.1891
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1791683 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9703. Min Act: -0.1700
Data Index: 4258749 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9703. Min Act: -0.1700
Data Index: 3256417 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9703. Min Act: -0.1700
Data Index: 4357843 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9703. Min Act: -0.1700
Data Index: 3753634 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9703. Min Act: -0.1700
Data Index: 8191599 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9390. Min Act: -0.1700
Data Index: 3917669 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9077. Min Act: -0.1700
Data Index: 7002901 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.8765. Min Act: -0.1700
Data Index: 2543141 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9077. Min Act: -0.1700
Data Index: 3006110 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.9077. Min Act: -0.1700
Data Index: 6304387 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1891. Min Range: -4.1891
Max Act: 3.8608. Min Act: -0.1700
Data Index: 8147567 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19