Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3389 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.5143. Min Act: -0.0000

Data Index: 1005217 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.3396. Min Act: -0.0000

Data Index: 625577 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.4400. Min Act: -0.0000

Data Index: 292469 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1396. Min Act: -0.0000

Data Index: 108 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1041. Min Act: -0.0000

Data Index: 608994 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0965. Min Act: -0.0000

Data Index: 392503 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0001. Min Act: -0.0000

Data Index: 286455 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1198434 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0279. Min Act: -0.0000

Data Index: 580564 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0520. Min Act: -0.0000

Data Index: 469406 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1280799 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1213207 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9649. Min Act: -0.0000

Data Index: 137173 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9004. Min Act: -0.0000

Data Index: 50125 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1005215 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9573. Min Act: -0.0000

Data Index: 427589 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9535. Min Act: -0.0000

Data Index: 257848 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9500. Min Act: -0.0000

Data Index: 745521 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9206. Min Act: -0.0000

Data Index: 563605 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9352. Min Act: -0.0000

Data Index: 913542 (C4 (Web Text))

Max Activating Token Index: 195