Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.6636. Min Act: -0.1700
Data Index: 8700521 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.6324. Min Act: -0.1700
Data Index: 1997366 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.3511. Min Act: -0.1700
Data Index: 8725690 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.3511. Min Act: -0.1700
Data Index: 4927378 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.2261. Min Act: -0.1700
Data Index: 6050273 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.1636. Min Act: -0.1700
Data Index: 730195 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.1636. Min Act: -0.1700
Data Index: 1390948 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.1636. Min Act: -0.1700
Data Index: 2511414 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.1324. Min Act: -0.1700
Data Index: 4488748 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.1324. Min Act: -0.1700
Data Index: 1571167 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.0386. Min Act: -0.1700
Data Index: 3617733 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.0074. Min Act: -0.1700
Data Index: 2170154 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.0386. Min Act: -0.1700
Data Index: 1822459 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.0074. Min Act: -0.1700
Data Index: 4512253 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6636. Min Range: -7.6636
Max Act: 6.9449. Min Act: -0.1700
Data Index: 3658269 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6636. Min Range: -7.6636
Max Act: 7.0386. Min Act: -0.1700
Data Index: 4615313 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6636. Min Range: -7.6636
Max Act: 6.8824. Min Act: -0.1700
Data Index: 3230969 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6636. Min Range: -7.6636
Max Act: 6.9761. Min Act: -0.1700
Data Index: 7862909 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6636. Min Range: -7.6636
Max Act: 6.9761. Min Act: -0.1700
Data Index: 7205235 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6636. Min Range: -7.6636
Max Act: 6.9449. Min Act: -0.1700
Data Index: 4594846 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19