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

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

Neuron 3602 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1005529 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1264335 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1249292 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3421. Min Act: -0.0000

Data Index: 958375 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3771. Min Act: -0.0000

Data Index: 1181220 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1055285 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3412. Min Act: -0.0000

Data Index: 706834 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3170. Min Act: -0.0000

Data Index: 29056 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3232. Min Act: -0.0000

Data Index: 717920 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3262. Min Act: -0.0000

Data Index: 286110 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3294. Min Act: -0.0000

Data Index: 503436 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1045939 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1420415 (Python Code)

Max Activating Token Index: 483

Text #13

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3146. Min Act: -0.0000

Data Index: 304864 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3356. Min Act: -0.0000

Data Index: 966178 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1052577 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3029. Min Act: -0.0000

Data Index: 451285 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1225046 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1255592 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.5737. Min Range: -0.5737

Max Act: 0.3210. Min Act: -0.0000

Data Index: 679859 (C4 (Web Text))

Max Activating Token Index: 540