Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.7037. Min Act: -0.0000

Data Index: 178479 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6576. Min Act: -0.0000

Data Index: 143821 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6322. Min Act: -0.0000

Data Index: 129002 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1081875 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6447. Min Act: -0.0000

Data Index: 120795 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6199. Min Act: -0.0000

Data Index: 792320 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6329. Min Act: -0.0000

Data Index: 765351 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1172359 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1607164 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1593461 (Python Code)

Max Activating Token Index: 763

Text #10

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5634. Min Act: -0.0000

Data Index: 879582 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5079. Min Act: -0.0000

Data Index: 639568 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5239. Min Act: -0.0000

Data Index: 507792 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1360400 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1465252 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5283. Min Act: -0.0000

Data Index: 246898 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1237048 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1386287 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5146. Min Act: -0.0001

Data Index: 915038 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4752. Min Act: -0.0001

Data Index: 1558824 (Python Code)

Max Activating Token Index: 634