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

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

Neuron 776 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: 0.1714. Min Range: -0.1714

Max Act: 0.1714. Min Act: -0.0002

Data Index: 639759 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1422. Min Act: -0.0002

Data Index: 578907 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1344. Min Act: -0.0001

Data Index: 303681 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1331. Min Act: -0.0001

Data Index: 473525 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1105034 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1324. Min Act: -0.0002

Data Index: 993164 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1297. Min Act: -0.0002

Data Index: 781461 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1255. Min Act: -0.0002

Data Index: 397850 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1299. Min Act: -0.0002

Data Index: 883894 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1204. Min Act: -0.0002

Data Index: 154854 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1241. Min Act: -0.0002

Data Index: 397179 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1155. Min Act: -0.0002

Data Index: 845046 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1209. Min Act: -0.0001

Data Index: 1544742 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1223. Min Act: -0.0002

Data Index: 783432 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1109056 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1252. Min Act: -0.0002

Data Index: 498499 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1567597 (Python Code)

Max Activating Token Index: 453

Text #17

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1259. Min Act: -0.0002

Data Index: 770087 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1330. Min Act: -0.0002

Data Index: 1309671 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1205. Min Act: -0.0002

Data Index: 114808 (C4 (Web Text))

Max Activating Token Index: 64