Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 12 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1095507 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3327. Min Act: -0.0000

Data Index: 232218 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1318883 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1270913 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1021436 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1349908 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1244572 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3198. Min Act: -0.0000

Data Index: 934824 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3085. Min Act: -0.0001

Data Index: 40436 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3341. Min Act: -0.0000

Data Index: 705428 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2994. Min Act: -0.0000

Data Index: 244501 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2943. Min Act: -0.0000

Data Index: 928268 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1060481 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3238. Min Act: -0.0000

Data Index: 174278 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1107671 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2988. Min Act: -0.0000

Data Index: 217843 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2865. Min Act: -0.0001

Data Index: 475337 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2964. Min Act: -0.0000

Data Index: 278659 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1065031 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.3553. Min Range: -0.3553

Max Act: 0.2810. Min Act: -0.0000

Data Index: 40165 (C4 (Web Text))

Max Activating Token Index: 328