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

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

Neuron 1266 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.6377. Min Act: -0.0000

Data Index: 891557 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.3180. Min Act: -0.0001

Data Index: 45876 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.3147. Min Act: -0.0001

Data Index: 836176 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9337. Min Act: -0.0000

Data Index: 987228 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9948. Min Act: -0.0001

Data Index: 926251 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9822. Min Act: -0.0000

Data Index: 655216 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.6377. Min Range: -1.6377

Max Act: 1.0136. Min Act: -0.0000

Data Index: 632190 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1249031 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9548. Min Act: -0.0000

Data Index: 15556 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9018. Min Act: -0.0000

Data Index: 458162 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1166981 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9448. Min Act: -0.0001

Data Index: 1191695 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9569. Min Act: -0.0000

Data Index: 118005 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9043. Min Act: -0.0001

Data Index: 643333 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9280. Min Act: -0.0001

Data Index: 471612 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1078405 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8411. Min Act: -0.0001

Data Index: 832770 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1213638 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1139977 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.6377. Min Range: -1.6377

Max Act: 0.8389. Min Act: -0.0001

Data Index: 1192209 (C4 (Web Text))

Max Activating Token Index: 417