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

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

Neuron 3628 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1335. Min Range: -2.1335

Max Act: 2.1335. Min Act: -0.0000

Data Index: 122042 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 2.1335. Min Range: -2.1335

Max Act: 2.0018. Min Act: -0.0000

Data Index: 368638 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 2.1335. Min Range: -2.1335

Max Act: 2.0382. Min Act: -0.0000

Data Index: 976332 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.8258. Min Act: -0.0000

Data Index: 93019 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.8031. Min Act: -0.0000

Data Index: 11383 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.8070. Min Act: -0.0000

Data Index: 53784 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.7230. Min Act: -0.0000

Data Index: 41035 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.7812. Min Act: -0.0000

Data Index: 125285 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.7161. Min Act: -0.0001

Data Index: 299542 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6399. Min Act: -0.0000

Data Index: 220625 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6591. Min Act: -0.0000

Data Index: 576574 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1142096 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5969. Min Act: -0.0000

Data Index: 882871 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6958. Min Act: -0.0000

Data Index: 1193383 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.7301. Min Act: -0.0000

Data Index: 682428 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5853. Min Act: -0.0000

Data Index: 501305 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6249. Min Act: -0.0000

Data Index: 651432 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.6448. Min Act: -0.0000

Data Index: 1164746 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1035458 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 2.1335. Min Range: -2.1335

Max Act: 1.5453. Min Act: -0.0000

Data Index: 449278 (C4 (Web Text))

Max Activating Token Index: 860