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

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

Neuron 1777 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 11.6042. Min Range: -11.6042

Max Act: 11.6042. Min Act: -0.0002

Data Index: 905648 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 11.6042. Min Range: -11.6042

Max Act: 8.4489. Min Act: -0.0002

Data Index: 805444 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 11.6042. Min Range: -11.6042

Max Act: 7.8496. Min Act: -0.0002

Data Index: 149511 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 11.6042. Min Range: -11.6042

Max Act: 7.6968. Min Act: -0.0002

Data Index: 239449 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 11.6042. Min Range: -11.6042

Max Act: 6.0518. Min Act: -0.0002

Data Index: 165141 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 11.6042. Min Range: -11.6042

Max Act: 6.1589. Min Act: -0.0002

Data Index: 508475 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 11.6042. Min Range: -11.6042

Max Act: 5.5231. Min Act: -0.0002

Data Index: 1257304 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 11.6042. Min Range: -11.6042

Max Act: 6.0423. Min Act: -0.0002

Data Index: 1078470 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 11.6042. Min Range: -11.6042

Max Act: 5.7138. Min Act: -0.0002

Data Index: 1289703 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 11.6042. Min Range: -11.6042

Max Act: 5.5793. Min Act: -0.0002

Data Index: 29395 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 11.6042. Min Range: -11.6042

Max Act: 6.0166. Min Act: -0.0002

Data Index: 762040 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 11.6042. Min Range: -11.6042

Max Act: 5.0236. Min Act: -0.0002

Data Index: 250457 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 11.6042. Min Range: -11.6042

Max Act: 5.1295. Min Act: -0.0002

Data Index: 547219 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 11.6042. Min Range: -11.6042

Max Act: 4.1642. Min Act: -0.0002

Data Index: 1033058 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 11.6042. Min Range: -11.6042

Max Act: 4.1908. Min Act: -0.0002

Data Index: 1055844 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 11.6042. Min Range: -11.6042

Max Act: 4.2996. Min Act: -0.0002

Data Index: 376180 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 11.6042. Min Range: -11.6042

Max Act: 4.2945. Min Act: -0.0002

Data Index: 760891 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 11.6042. Min Range: -11.6042

Max Act: 4.1924. Min Act: -0.0002

Data Index: 696873 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 11.6042. Min Range: -11.6042

Max Act: 4.1455. Min Act: -0.0002

Data Index: 1168059 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 11.6042. Min Range: -11.6042

Max Act: 4.4813. Min Act: -0.0002

Data Index: 339426 (C4 (Web Text))

Max Activating Token Index: 513