Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.9748. Min Act: -0.1700
Data Index: 6894096 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.6623. Min Act: -0.1700
Data Index: 456961 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.6623. Min Act: -0.1700
Data Index: 2616048 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.6623. Min Act: -0.1700
Data Index: 4490192 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.6623. Min Act: -0.1700
Data Index: 3566477 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.5998. Min Act: -0.1700
Data Index: 5416264 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.5373. Min Act: -0.1700
Data Index: 250177 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.4748. Min Act: -0.1700
Data Index: 1759844 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.4748. Min Act: -0.1700
Data Index: 8515939 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.4748. Min Act: -0.1700
Data Index: 3207078 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.4748. Min Act: -0.1700
Data Index: 4472321 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.4123. Min Act: -0.1700
Data Index: 1741718 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.4123. Min Act: -0.1700
Data Index: 7163094 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.3498. Min Act: -0.1700
Data Index: 6384410 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.3498. Min Act: -0.1700
Data Index: 2857877 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.3498. Min Act: -0.1700
Data Index: 4208783 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.3498. Min Act: -0.1700
Data Index: 4830159 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.2873. Min Act: -0.1700
Data Index: 6565229 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.2873. Min Act: -0.1700
Data Index: 4332379 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9748. Min Range: -8.9748
Max Act: 8.2873. Min Act: -0.1700
Data Index: 2856132 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19