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

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

Neuron 4679 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.2276. Min Act: -0.0000

Data Index: 305817 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.1536. Min Act: -0.0000

Data Index: 633537 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.2134. Min Act: -0.0000

Data Index: 624339 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.0806. Min Act: -0.0000

Data Index: 378820 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1060901 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.1544. Min Act: -0.0000

Data Index: 396553 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1098699 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.0440. Min Act: -0.0000

Data Index: 58478 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.0368. Min Act: -0.0000

Data Index: 750197 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.0140. Min Act: -0.0000

Data Index: 1240741 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1153969 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9813. Min Act: -0.0000

Data Index: 94276 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1247978 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9926. Min Act: -0.0000

Data Index: 420976 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1253379 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9503. Min Act: -0.0000

Data Index: 744429 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8940. Min Act: -0.0000

Data Index: 982349 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9513. Min Act: -0.0000

Data Index: 467446 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1344700 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9380. Min Act: -0.0000

Data Index: 262999 (C4 (Web Text))

Max Activating Token Index: 590