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

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

Neuron 180 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4943. Min Act: -0.0003

Data Index: 688067 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4182. Min Act: -0.0003

Data Index: 176877 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4402. Min Act: -0.0003

Data Index: 387263 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4483. Min Act: -0.0003

Data Index: 406803 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4347. Min Act: -0.0003

Data Index: 589442 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4160. Min Act: -0.0003

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4476. Min Act: -0.0003

Data Index: 408484 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4289. Min Act: -0.0003

Data Index: 1151233 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4542. Min Act: -0.0003

Data Index: 688919 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4396. Min Act: -0.0003

Data Index: 772649 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4384. Min Act: -0.0003

Data Index: 1305496 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4353. Min Act: -0.0003

Data Index: 633202 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4227. Min Act: -0.0003

Data Index: 281307 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4227. Min Act: -0.0003

Data Index: 510418 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4503. Min Act: -0.0003

Data Index: 262553 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4192. Min Act: -0.0003

Data Index: 811821 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4204. Min Act: -0.0003

Data Index: 1258741 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4168. Min Act: -0.0003

Data Index: 1080509 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4004. Min Act: -0.0003

Data Index: 750140 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.4943. Min Range: -0.4943

Max Act: 0.4140. Min Act: -0.0003

Data Index: 1158847 (C4 (Web Text))

Max Activating Token Index: 601