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

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

Neuron 4673 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: 6.1179. Min Range: -6.1179

Max Act: 6.1179. Min Act: -0.0000

Data Index: 594723 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.9263. Min Act: -0.0000

Data Index: 1239603 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 6.1179. Min Range: -6.1179

Max Act: 5.0937. Min Act: -0.0000

Data Index: 604090 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 6.1179. Min Range: -6.1179

Max Act: 5.0667. Min Act: -0.0000

Data Index: 529710 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.9272. Min Act: -0.0000

Data Index: 1357301 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.6704. Min Act: -0.0000

Data Index: 779124 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.3385. Min Act: -0.0000

Data Index: 516125 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.4487. Min Act: -0.0000

Data Index: 237794 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.4439. Min Act: -0.0000

Data Index: 1160863 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.3757. Min Act: -0.0000

Data Index: 148578 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.3474. Min Act: -0.0000

Data Index: 832678 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.1891. Min Act: -0.0000

Data Index: 1068421 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.4280. Min Act: -0.0000

Data Index: 215133 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.2066. Min Act: -0.0000

Data Index: 891387 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.3377. Min Act: -0.0000

Data Index: 675905 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.1682. Min Act: -0.0000

Data Index: 1048874 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.1428. Min Act: -0.0000

Data Index: 222464 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 6.1179. Min Range: -6.1179

Max Act: 3.9827. Min Act: -0.0000

Data Index: 35707 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.2844. Min Act: -0.0000

Data Index: 22833 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 6.1179. Min Range: -6.1179

Max Act: 4.1170. Min Act: -0.0000

Data Index: 552065 (C4 (Web Text))

Max Activating Token Index: 322