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

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

Neuron 221 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.9574. Min Act: -0.0001

Data Index: 489941 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.9579. Min Act: -0.0001

Data Index: 1302938 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.9435. Min Act: -0.0001

Data Index: 425828 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.9144. Min Act: -0.0001

Data Index: 793626 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8306. Min Act: -0.0001

Data Index: 812198 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8201. Min Act: -0.0001

Data Index: 956079 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7921. Min Act: -0.0001

Data Index: 1103061 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8181. Min Act: -0.0001

Data Index: 251864 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7635. Min Act: -0.0001

Data Index: 942664 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8046. Min Act: -0.0001

Data Index: 639623 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7366. Min Act: -0.0001

Data Index: 785207 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7496. Min Act: -0.0001

Data Index: 13329 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7564. Min Act: -0.0001

Data Index: 192423 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7870. Min Act: -0.0001

Data Index: 1309963 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7412. Min Act: -0.0001

Data Index: 1048980 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7887. Min Act: -0.0001

Data Index: 298835 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7183. Min Act: -0.0001

Data Index: 403585 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7425. Min Act: -0.0001

Data Index: 564420 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7429. Min Act: -0.0001

Data Index: 970480 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7188. Min Act: -0.0001

Data Index: 188931 (C4 (Web Text))

Max Activating Token Index: 369