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

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

Neuron 2916 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.6152. Min Act: -0.0000

Data Index: 345247 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.5233. Min Act: -0.0000

Data Index: 12099 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1053816 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4582. Min Act: -0.0000

Data Index: 29161 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1190760 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4724. Min Act: -0.0000

Data Index: 37183 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1508335 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4130. Min Act: -0.0000

Data Index: 217163 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1249351 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3755. Min Act: -0.0000

Data Index: 441262 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1272525 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.4114. Min Act: -0.0000

Data Index: 516917 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3520. Min Act: -0.0000

Data Index: 60239 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3753. Min Act: -0.0000

Data Index: 948357 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1614797 (Python Code)

Max Activating Token Index: 911

Text #15

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3609. Min Act: -0.0000

Data Index: 749476 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1430918 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3629. Min Act: -0.0000

Data Index: 599218 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1269171 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.6152. Min Range: -0.6152

Max Act: 0.3329. Min Act: -0.0000

Data Index: 267656 (C4 (Web Text))

Max Activating Token Index: 712