Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 546 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.9190. Min Act: -0.1700
Data Index: 1275943 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8714. Min Act: -0.1700
Data Index: 1264413 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8555. Min Act: -0.1700
Data Index: 1131541 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8396. Min Act: -0.1700
Data Index: 433824 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8396. Min Act: -0.1700
Data Index: 918470 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8237. Min Act: -0.1700
Data Index: 1322577 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8237. Min Act: -0.1700
Data Index: 641217 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8078. Min Act: -0.1700
Data Index: 343618 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8078. Min Act: -0.1700
Data Index: 786019 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8078. Min Act: -0.1700
Data Index: 1181862 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.7918. Min Act: -0.1700
Data Index: 1145409 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.7918. Min Act: -0.1700
Data Index: 391333 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.7918. Min Act: -0.1700
Data Index: 95998 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.7918. Min Act: -0.1700
Data Index: 565506 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.7918. Min Act: -0.1700
Data Index: 627613 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8078. Min Act: -0.1700
Data Index: 544207 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8078. Min Act: -0.1700
Data Index: 794319 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.8078. Min Act: -0.1700
Data Index: 354975 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.7918. Min Act: -0.1700
Data Index: 193281 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9190. Min Range: -2.9190
Max Act: 2.7918. Min Act: -0.1700
Data Index: 401277 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19