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

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

Neuron 1477 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.7179. Min Act: -0.0000

Data Index: 114898 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.5980. Min Act: -0.0000

Data Index: 120358 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.5901. Min Act: -0.0000

Data Index: 700506 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4778. Min Act: -0.0000

Data Index: 987677 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4841. Min Act: -0.0000

Data Index: 506464 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4654. Min Act: 0.0000

Data Index: 1036879 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4436. Min Act: -0.0000

Data Index: 459 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4376. Min Act: -0.0000

Data Index: 684483 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1301508 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4174. Min Act: -0.0000

Data Index: 602742 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1233324 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1102070 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.3852. Min Act: -0.0000

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.4215. Min Act: -0.0000

Data Index: 729867 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.3898. Min Act: -0.0000

Data Index: 499578 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.3731. Min Act: -0.0000

Data Index: 498285 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1260489 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.3469. Min Act: -0.0000

Data Index: 615311 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.7179. Min Range: -0.7179

Max Act: 0.3889. Min Act: -0.0000

Data Index: 118974 (C4 (Web Text))

Max Activating Token Index: 824