Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5050 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.0366. Min Range: -4.0366

Max Act: 4.0366. Min Act: -0.0000

Data Index: 509009 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.9185. Min Act: -0.0000

Data Index: 264435 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.6712. Min Act: -0.0000

Data Index: 439249 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.6429. Min Act: -0.0000

Data Index: 1194574 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.6152. Min Act: -0.0000

Data Index: 119797 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.6112. Min Act: -0.0000

Data Index: 854225 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.3475. Min Act: -0.0000

Data Index: 173966 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.4802. Min Act: -0.0000

Data Index: 1140096 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.4079. Min Act: -0.0000

Data Index: 518904 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.5016. Min Act: -0.0000

Data Index: 252016 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 4.0366. Min Range: -4.0366

Max Act: 2.8722. Min Act: -0.0000

Data Index: 257104 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.1326. Min Act: -0.0000

Data Index: 1264034 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.3713. Min Act: -0.0000

Data Index: 594676 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 4.0366. Min Range: -4.0366

Max Act: 2.9924. Min Act: -0.0000

Data Index: 643767 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.0539. Min Act: -0.0000

Data Index: 1132079 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 4.0366. Min Range: -4.0366

Max Act: 2.9580. Min Act: -0.0000

Data Index: 1020598 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 4.0366. Min Range: -4.0366

Max Act: 3.0658. Min Act: -0.0000

Data Index: 624709 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 4.0366. Min Range: -4.0366

Max Act: 2.7642. Min Act: -0.0000

Data Index: 267812 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 4.0366. Min Range: -4.0366

Max Act: 2.6178. Min Act: -0.0000

Data Index: 117998 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 4.0366. Min Range: -4.0366

Max Act: 2.7060. Min Act: -0.0000

Data Index: 321757 (C4 (Web Text))

Max Activating Token Index: 437