Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1880 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.1331. Min Range: -5.1331

Max Act: 5.1249. Min Act: -0.0002

Data Index: 95219 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 5.1331. Min Range: -5.1331

Max Act: 5.1331. Min Act: -0.0001

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 5.1331. Min Range: -5.1331

Max Act: 5.1055. Min Act: -0.0001

Data Index: 682063 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.8740. Min Act: -0.0002

Data Index: 374718 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.7300. Min Act: -0.0001

Data Index: 1238274 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4266. Min Act: -0.0001

Data Index: 1255118 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.5289. Min Act: -0.0001

Data Index: 106657 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.1137. Min Act: -0.0001

Data Index: 376610 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.2253. Min Act: -0.0001

Data Index: 937956 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.1355. Min Act: -0.0001

Data Index: 1069654 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.0318. Min Act: -0.0001

Data Index: 285750 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 5.1331. Min Range: -5.1331

Max Act: 3.8599. Min Act: -0.0001

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.0207. Min Act: -0.0001

Data Index: 1462965 (Python Code)

Max Activating Token Index: 750

Text #13

Max Range: 5.1331. Min Range: -5.1331

Max Act: 3.6916. Min Act: -0.0001

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.4455. Min Act: -0.0001

Data Index: 863847 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 5.1331. Min Range: -5.1331

Max Act: 3.7622. Min Act: -0.0002

Data Index: 1106016 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 5.1331. Min Range: -5.1331

Max Act: 3.7854. Min Act: -0.0001

Data Index: 8750 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 5.1331. Min Range: -5.1331

Max Act: 3.9409. Min Act: -0.0001

Data Index: 570442 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.2406. Min Act: -0.0001

Data Index: 499331 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 5.1331. Min Range: -5.1331

Max Act: 4.8666. Min Act: -0.0002

Data Index: 1206080 (C4 (Web Text))

Max Activating Token Index: 520