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

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

Neuron 217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1183817 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5885. Min Act: -0.0000

Data Index: 851794 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5912. Min Act: -0.0000

Data Index: 416649 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5582. Min Act: -0.0000

Data Index: 599328 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1246875 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5104. Min Act: -0.0000

Data Index: 353586 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1061147 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1233469 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1278515 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5097. Min Act: -0.0000

Data Index: 866185 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5042. Min Act: -0.0000

Data Index: 713313 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4991. Min Act: -0.0000

Data Index: 893244 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4827. Min Act: -0.0000

Data Index: 505607 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4967. Min Act: -0.0000

Data Index: 157582 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4849. Min Act: -0.0000

Data Index: 418980 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1270876 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1201157 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1112444 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1028043 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4926. Min Act: -0.0000

Data Index: 451160 (C4 (Web Text))

Max Activating Token Index: 851