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

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

Neuron 2875 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6666. Min Act: -0.0001

Data Index: 464288 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6351. Min Act: -0.0001

Data Index: 695869 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6335. Min Act: -0.0001

Data Index: 1022370 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6563. Min Act: -0.0001

Data Index: 724653 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5946. Min Act: -0.0001

Data Index: 1018446 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5701. Min Act: -0.0001

Data Index: 179208 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5503. Min Act: -0.0001

Data Index: 482254 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5829. Min Act: -0.0001

Data Index: 800002 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5192. Min Act: -0.0001

Data Index: 656605 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1655808 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5124. Min Act: -0.0001

Data Index: 1025033 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5464. Min Act: -0.0001

Data Index: 831928 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5181. Min Act: -0.0001

Data Index: 535896 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1058924 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5311. Min Act: -0.0001

Data Index: 881824 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5140. Min Act: -0.0001

Data Index: 163935 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1130645 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4394. Min Act: -0.0001

Data Index: 1225837 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1484543 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4815. Min Act: -0.0001

Data Index: 491300 (C4 (Web Text))

Max Activating Token Index: 193