Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 469 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.4361. Min Act: -0.0001

Data Index: 1046367 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.4404. Min Act: -0.0001

Data Index: 1017154 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.4132. Min Act: -0.0001

Data Index: 189517 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3858. Min Act: -0.0001

Data Index: 821815 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.4018. Min Act: -0.0001

Data Index: 484269 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3554. Min Act: -0.0001

Data Index: 145952 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3522. Min Act: -0.0001

Data Index: 976191 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3418. Min Act: -0.0001

Data Index: 435387 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3429. Min Act: -0.0001

Data Index: 409420 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3404. Min Act: -0.0001

Data Index: 423522 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1002559 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3482. Min Act: -0.0001

Data Index: 1323647 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3469. Min Act: -0.0001

Data Index: 165389 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3260. Min Act: -0.0001

Data Index: 824462 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3324. Min Act: -0.0001

Data Index: 719936 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.2991. Min Act: -0.0001

Data Index: 281392 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3247. Min Act: -0.0001

Data Index: 1122659 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3175. Min Act: -0.0001

Data Index: 763764 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3364. Min Act: -0.0001

Data Index: 431836 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3122. Min Act: -0.0001

Data Index: 81322 (C4 (Web Text))

Max Activating Token Index: 492