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

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

Neuron 466 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.6422. Min Act: -0.0000

Data Index: 1241663 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.4304. Min Act: -0.0000

Data Index: 1089817 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.3613. Min Act: -0.0000

Data Index: 915279 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.2734. Min Act: -0.0000

Data Index: 1197698 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.2343. Min Act: -0.0000

Data Index: 1057109 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.1023. Min Act: -0.0000

Data Index: 672828 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.2328. Min Act: -0.0000

Data Index: 448062 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.1467. Min Act: -0.0000

Data Index: 24591 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.9985. Min Act: -0.0000

Data Index: 496927 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.9626. Min Act: -0.0000

Data Index: 1021604 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 2.6422. Min Range: -2.6422

Max Act: 2.1150. Min Act: -0.0000

Data Index: 70508 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.7506. Min Act: -0.0000

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.9440. Min Act: -0.0000

Data Index: 1225349 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.8295. Min Act: -0.0000

Data Index: 460153 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.9227. Min Act: -0.0000

Data Index: 422115 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.8045. Min Act: -0.0000

Data Index: 186 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.8854. Min Act: -0.0000

Data Index: 694103 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.6638. Min Act: -0.0000

Data Index: 1269611 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.7490. Min Act: -0.0000

Data Index: 391096 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 2.6422. Min Range: -2.6422

Max Act: 1.8075. Min Act: -0.0000

Data Index: 494468 (C4 (Web Text))

Max Activating Token Index: 167