Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1609. Min Range: -4.1609
Max Act: 4.1609. Min Act: -0.1700
Data Index: 4831794 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1609. Min Range: -4.1609
Max Act: 4.0671. Min Act: -0.1700
Data Index: 4279923 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.9733. Min Act: -0.1700
Data Index: 508713 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.9108. Min Act: -0.1700
Data Index: 6973464 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8795. Min Act: -0.1700
Data Index: 1399370 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8483. Min Act: -0.1700
Data Index: 3977926 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8795. Min Act: -0.1700
Data Index: 6606680 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7857. Min Act: -0.1700
Data Index: 3855298 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8170. Min Act: -0.1700
Data Index: 1558455 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8170. Min Act: -0.1700
Data Index: 4572518 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8170. Min Act: -0.1700
Data Index: 5292299 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8170. Min Act: -0.1700
Data Index: 3788295 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.8170. Min Act: -0.1700
Data Index: 2436307 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7857. Min Act: -0.1700
Data Index: 6966283 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7857. Min Act: -0.1700
Data Index: 7533408 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7544. Min Act: -0.1700
Data Index: 577973 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7544. Min Act: -0.1700
Data Index: 5618371 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7544. Min Act: -0.1700
Data Index: 1742987 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7857. Min Act: -0.1700
Data Index: 6738852 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1609. Min Range: -4.1609
Max Act: 3.7544. Min Act: -0.1700
Data Index: 680016 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19