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

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

Neuron 1830 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6860. Min Act: -0.0000

Data Index: 945341 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6044. Min Act: -0.0000

Data Index: 438470 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5997. Min Act: -0.0000

Data Index: 253553 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5754. Min Act: -0.0000

Data Index: 647054 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5740. Min Act: -0.0000

Data Index: 726283 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5694. Min Act: -0.0000

Data Index: 1269915 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.6042. Min Act: -0.0000

Data Index: 961747 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5932. Min Act: -0.0000

Data Index: 267843 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1042426 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5699. Min Act: -0.0000

Data Index: 156288 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5236. Min Act: -0.0000

Data Index: 895232 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5419. Min Act: -0.0000

Data Index: 864660 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1161633 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1049325 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1348678 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5426. Min Act: -0.0000

Data Index: 327022 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1337575 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5040. Min Act: -0.0000

Data Index: 407429 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5188. Min Act: -0.0000

Data Index: 787427 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.6860. Min Range: -0.6860

Max Act: 0.5302. Min Act: -0.0000

Data Index: 865610 (C4 (Web Text))

Max Activating Token Index: 416