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

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

Neuron 3827 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: 1.8423. Min Range: -1.8423

Max Act: 1.6800. Min Act: -0.0001

Data Index: 1150589 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.8130. Min Act: -0.0001

Data Index: 412880 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.8423. Min Act: -0.0001

Data Index: 80033 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.5569. Min Act: -0.0001

Data Index: 441842 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.5306. Min Act: -0.0001

Data Index: 862934 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.5666. Min Act: -0.0001

Data Index: 757552 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.5656. Min Act: -0.0001

Data Index: 625340 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4663. Min Act: -0.0001

Data Index: 896859 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4983. Min Act: -0.0001

Data Index: 237467 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4882. Min Act: -0.0001

Data Index: 282928 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4838. Min Act: -0.0001

Data Index: 66166 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4420. Min Act: -0.0001

Data Index: 682162 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.5147. Min Act: -0.0001

Data Index: 1099936 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.3828. Min Act: -0.0001

Data Index: 353973 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4404. Min Act: -0.0001

Data Index: 371398 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4034. Min Act: -0.0001

Data Index: 1166577 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4628. Min Act: -0.0001

Data Index: 15125 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.4673. Min Act: -0.0001

Data Index: 42291 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.3351. Min Act: -0.0001

Data Index: 184438 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.8423. Min Range: -1.8423

Max Act: 1.3948. Min Act: -0.0001

Data Index: 219003 (C4 (Web Text))

Max Activating Token Index: 196