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

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

Neuron 2618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.4202. Min Act: -0.0001

Data Index: 855650 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3871. Min Act: -0.0001

Data Index: 359293 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3575. Min Act: -0.0001

Data Index: 98096 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3745. Min Act: -0.0001

Data Index: 475204 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3452. Min Act: -0.0001

Data Index: 1130598 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3464. Min Act: -0.0001

Data Index: 542240 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3476. Min Act: -0.0001

Data Index: 542438 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3385. Min Act: -0.0001

Data Index: 81602 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3439. Min Act: -0.0001

Data Index: 268129 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3426. Min Act: -0.0001

Data Index: 753255 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3400. Min Act: -0.0001

Data Index: 275441 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1094531 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3465. Min Act: -0.0001

Data Index: 1253691 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3116. Min Act: -0.0001

Data Index: 538773 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3157. Min Act: -0.0001

Data Index: 38516 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3162. Min Act: -0.0001

Data Index: 1110590 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1271130 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3308. Min Act: -0.0001

Data Index: 1739 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3000. Min Act: -0.0001

Data Index: 662416 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3285. Min Act: -0.0001

Data Index: 744529 (C4 (Web Text))

Max Activating Token Index: 542