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

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

Neuron 1091 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4996. Min Act: -0.0000

Data Index: 792819 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4773. Min Act: -0.0001

Data Index: 1233347 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4550. Min Act: -0.0000

Data Index: 556088 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4613. Min Act: -0.0001

Data Index: 463900 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4708. Min Act: -0.0001

Data Index: 1253153 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4360. Min Act: -0.0001

Data Index: 1248258 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4491. Min Act: -0.0000

Data Index: 964856 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4407. Min Act: -0.0000

Data Index: 660176 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4530. Min Act: -0.0001

Data Index: 482939 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1339937 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4383. Min Act: -0.0000

Data Index: 647975 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1207808 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4360. Min Act: -0.0001

Data Index: 1146048 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4182. Min Act: -0.0000

Data Index: 223336 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4159. Min Act: -0.0000

Data Index: 650690 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4157. Min Act: -0.0001

Data Index: 635157 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4122. Min Act: -0.0001

Data Index: 292809 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4097. Min Act: -0.0001

Data Index: 398097 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4230. Min Act: -0.0000

Data Index: 549594 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4216. Min Act: -0.0001

Data Index: 1154616 (C4 (Web Text))

Max Activating Token Index: 595