Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3874 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6700. Min Act: -0.0001

Data Index: 260508 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.6399. Min Act: -0.0001

Data Index: 1355239 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 3.6700. Min Range: -3.6700

Max Act: 3.3294. Min Act: -0.0001

Data Index: 976812 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.6549. Min Act: -0.0001

Data Index: 195974 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.7703. Min Act: -0.0001

Data Index: 273298 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.7770. Min Act: -0.0001

Data Index: 158196 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.5719. Min Act: -0.0001

Data Index: 1022209 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.6358. Min Act: -0.0001

Data Index: 624032 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.7704. Min Act: -0.0001

Data Index: 723310 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.4960. Min Act: -0.0001

Data Index: 209124 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.6009. Min Act: -0.0001

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.6141. Min Act: -0.0001

Data Index: 1347423 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.6158. Min Act: -0.0001

Data Index: 72557 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.5869. Min Act: -0.0001

Data Index: 590916 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.6773. Min Act: -0.0001

Data Index: 259063 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.3743. Min Act: -0.0001

Data Index: 1249323 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.4810. Min Act: -0.0001

Data Index: 158169 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.3486. Min Act: -0.0001

Data Index: 1279875 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.4539. Min Act: -0.0001

Data Index: 506593 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 3.6700. Min Range: -3.6700

Max Act: 2.2988. Min Act: -0.0001

Data Index: 1096916 (C4 (Web Text))

Max Activating Token Index: 716