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

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

Neuron 147 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.1179. Min Act: -0.0000

Data Index: 411540 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9865. Min Act: 0.0000

Data Index: 646496 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.0444. Min Act: -0.0000

Data Index: 246922 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9650. Min Act: 0.0000

Data Index: 432278 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8911. Min Act: 0.0000

Data Index: 545008 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9435. Min Act: -0.0000

Data Index: 282261 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1118354 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1111080 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8959. Min Act: 0.0000

Data Index: 836544 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8652. Min Act: 0.0000

Data Index: 155770 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8368. Min Act: -0.0000

Data Index: 325321 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8604. Min Act: -0.0000

Data Index: 204772 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8782. Min Act: 0.0000

Data Index: 206963 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8615. Min Act: 0.0000

Data Index: 1191560 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1190461 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8292. Min Act: 0.0000

Data Index: 1323727 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8159. Min Act: -0.0000

Data Index: 599074 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8236. Min Act: 0.0000

Data Index: 875309 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7871. Min Act: 0.0000

Data Index: 440836 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7660. Min Act: 0.0000

Data Index: 639285 (C4 (Web Text))

Max Activating Token Index: 315