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

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

Neuron 3213 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.4203. Min Act: -0.0001

Data Index: 372657 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.2487. Min Act: -0.0001

Data Index: 1110921 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.2231. Min Act: -0.0001

Data Index: 940433 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.2163. Min Act: -0.0001

Data Index: 1323268 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0671. Min Act: -0.0001

Data Index: 954446 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1352. Min Act: -0.0001

Data Index: 468879 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0442. Min Act: -0.0001

Data Index: 1005993 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.1146. Min Act: -0.0001

Data Index: 63617 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0100. Min Act: -0.0001

Data Index: 1095374 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0665. Min Act: -0.0001

Data Index: 397950 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9938. Min Act: -0.0001

Data Index: 1311307 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0376. Min Act: -0.0001

Data Index: 197065 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0062. Min Act: -0.0001

Data Index: 612166 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9596. Min Act: -0.0001

Data Index: 787089 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9805. Min Act: -0.0001

Data Index: 552905 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.4203. Min Range: -1.4203

Max Act: 1.0010. Min Act: -0.0001

Data Index: 1315419 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9455. Min Act: -0.0001

Data Index: 1354479 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9632. Min Act: -0.0001

Data Index: 1301475 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9940. Min Act: -0.0001

Data Index: 1045315 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.4203. Min Range: -1.4203

Max Act: 0.9376. Min Act: -0.0001

Data Index: 886985 (C4 (Web Text))

Max Activating Token Index: 637