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

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

Neuron 5267 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: 0.9358. Min Range: -0.9358

Max Act: 0.9358. Min Act: -0.0000

Data Index: 407409 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.8253. Min Act: -0.0000

Data Index: 173084 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.7772. Min Act: -0.0000

Data Index: 166623 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.6215. Min Act: -0.0000

Data Index: 220224 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.6070. Min Act: -0.0000

Data Index: 585198 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.6073. Min Act: -0.0000

Data Index: 710163 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1310424 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1238160 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5433. Min Act: -0.0000

Data Index: 68730 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5365. Min Act: -0.0000

Data Index: 95523 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5488. Min Act: -0.0000

Data Index: 963861 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5265. Min Act: -0.0000

Data Index: 497978 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1116143 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5213. Min Act: -0.0000

Data Index: 639932 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4996. Min Act: -0.0000

Data Index: 983254 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5212. Min Act: -0.0000

Data Index: 248650 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.5019. Min Act: -0.0000

Data Index: 554595 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1178597 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1338401 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.9358. Min Range: -0.9358

Max Act: 0.4958. Min Act: -0.0000

Data Index: 621487 (C4 (Web Text))

Max Activating Token Index: 589