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

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

Neuron 2782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.8205. Min Act: -0.0000

Data Index: 810216 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.7893. Min Act: -0.0000

Data Index: 352470 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.7957. Min Act: 0.0000

Data Index: 76668 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1281994 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1216334 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.6956. Min Act: -0.0000

Data Index: 686950 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1323136 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5994. Min Act: -0.0000

Data Index: 214661 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.6070. Min Act: -0.0000

Data Index: 245211 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1173942 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5368. Min Act: -0.0000

Data Index: 764379 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5906. Min Act: -0.0001

Data Index: 205783 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5793. Min Act: -0.0000

Data Index: 17105 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5766. Min Act: -0.0000

Data Index: 447608 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5584. Min Act: -0.0000

Data Index: 121893 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5588. Min Act: -0.0000

Data Index: 345346 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5352. Min Act: -0.0000

Data Index: 929793 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5466. Min Act: -0.0000

Data Index: 812218 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5635. Min Act: 0.0000

Data Index: 816933 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.8205. Min Range: -0.8205

Max Act: 0.5405. Min Act: -0.0000

Data Index: 248822 (C4 (Web Text))

Max Activating Token Index: 986