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

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

Neuron 5485 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.7178. Min Act: -0.0000

Data Index: 68170 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.5094. Min Act: -0.0000

Data Index: 910754 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4776. Min Act: -0.0000

Data Index: 84481 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.4631. Min Act: -0.0000

Data Index: 897742 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3857. Min Act: -0.0000

Data Index: 224116 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1175349 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1002218 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3046. Min Act: -0.0000

Data Index: 858101 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3187. Min Act: -0.0000

Data Index: 489260 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.3170. Min Act: -0.0000

Data Index: 805702 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2596. Min Act: -0.0000

Data Index: 681023 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2376. Min Act: -0.0000

Data Index: 380241 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2313. Min Act: -0.0000

Data Index: 318573 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2407. Min Act: -0.0000

Data Index: 879669 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2179. Min Act: -0.0000

Data Index: 602677 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2202. Min Act: -0.0000

Data Index: 588980 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1271303 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2056. Min Act: -0.0000

Data Index: 430910 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.2037. Min Act: -0.0000

Data Index: 618387 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.7178. Min Range: -0.7178

Max Act: 0.1991. Min Act: -0.0000

Data Index: 39214 (C4 (Web Text))

Max Activating Token Index: 27