Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3851. Min Act: -0.0001

Data Index: 353681 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3406. Min Act: 0.0001

Data Index: 434880 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3474. Min Act: -0.0001

Data Index: 472009 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3468. Min Act: -0.0000

Data Index: 437155 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3353. Min Act: -0.0000

Data Index: 613224 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1316674 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1345270 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3319. Min Act: -0.0000

Data Index: 916287 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3391. Min Act: -0.0000

Data Index: 403416 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3169. Min Act: -0.0000

Data Index: 563449 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3236. Min Act: 0.0001

Data Index: 1126960 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3126. Min Act: -0.0000

Data Index: 594390 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3210. Min Act: -0.0000

Data Index: 517100 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3185. Min Act: 0.0000

Data Index: 646268 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3176. Min Act: -0.0000

Data Index: 91237 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3243. Min Act: -0.0000

Data Index: 687949 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3130. Min Act: -0.0000

Data Index: 867417 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3146. Min Act: -0.0000

Data Index: 648903 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3096. Min Act: 0.0001

Data Index: 846472 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2977. Min Act: -0.0001

Data Index: 1034715 (C4 (Web Text))

Max Activating Token Index: 924