Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 378 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.5983. Min Act: -0.1700
Data Index: 6531495 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.2858. Min Act: -0.1700
Data Index: 7892587 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.3483. Min Act: -0.1700
Data Index: 7818207 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.0983. Min Act: -0.1700
Data Index: 447147 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.0983. Min Act: -0.1700
Data Index: 7148056 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.0983. Min Act: -0.1700
Data Index: 1438849 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.0358. Min Act: -0.1700
Data Index: 4449767 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.0358. Min Act: -0.1700
Data Index: 1479013 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5983. Min Range: -8.5983
Max Act: 8.0358. Min Act: -0.1700
Data Index: 6472285 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9733. Min Act: -0.1700
Data Index: 6642592 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9108. Min Act: -0.1700
Data Index: 523650 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9733. Min Act: -0.1700
Data Index: 5672292 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9108. Min Act: -0.1700
Data Index: 2034747 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9108. Min Act: -0.1700
Data Index: 7872035 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9108. Min Act: -0.1700
Data Index: 48483 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9108. Min Act: -0.1700
Data Index: 4089709 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9108. Min Act: -0.1700
Data Index: 4472809 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.9108. Min Act: -0.1700
Data Index: 4792838 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.7858. Min Act: -0.1700
Data Index: 4160081 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5983. Min Range: -8.5983
Max Act: 7.8483. Min Act: -0.1700
Data Index: 2517944 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19