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

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

Neuron 497 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.9344. Min Act: -0.0001

Data Index: 410017 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.9030. Min Act: -0.0001

Data Index: 292238 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.9122. Min Act: -0.0001

Data Index: 988199 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8773. Min Act: -0.0001

Data Index: 314666 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.7429. Min Act: -0.0001

Data Index: 640197 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8256. Min Act: -0.0001

Data Index: 573059 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8514. Min Act: -0.0001

Data Index: 321349 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8346. Min Act: -0.0001

Data Index: 1119487 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8059. Min Act: -0.0001

Data Index: 400207 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8544. Min Act: -0.0001

Data Index: 882340 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8490. Min Act: -0.0001

Data Index: 287015 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8231. Min Act: -0.0001

Data Index: 497986 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8139. Min Act: -0.0001

Data Index: 212301 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8055. Min Act: -0.0001

Data Index: 1191043 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8079. Min Act: -0.0001

Data Index: 249477 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1198144 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8941. Min Act: -0.0001

Data Index: 279757 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.7952. Min Act: -0.0001

Data Index: 411807 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8086. Min Act: -0.0001

Data Index: 933549 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.9344. Min Range: -0.9344

Max Act: 0.8013. Min Act: -0.0001

Data Index: 1095298 (C4 (Web Text))

Max Activating Token Index: 432