Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 424 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2168. Min Range: -2.2168

Max Act: 2.2168. Min Act: -0.0000

Data Index: 1003446 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.7444. Min Act: -0.0000

Data Index: 265550 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.6779. Min Act: -0.0000

Data Index: 567979 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.6211. Min Act: -0.0000

Data Index: 1306938 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.5059. Min Act: -0.0000

Data Index: 450948 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.2454. Min Act: -0.0000

Data Index: 512114 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.4733. Min Act: -0.0000

Data Index: 493348 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1046882 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1123200 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.2795. Min Act: -0.0000

Data Index: 568821 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.3455. Min Act: -0.0000

Data Index: 1198446 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.1896. Min Act: -0.0000

Data Index: 912481 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1057819 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1280278 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.2457. Min Act: -0.0000

Data Index: 1076125 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1092048 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1132671 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.2921. Min Act: -0.0000

Data Index: 329896 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.3734. Min Act: -0.0000

Data Index: 514201 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.4376. Min Act: -0.0000

Data Index: 683849 (C4 (Web Text))

Max Activating Token Index: 244