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

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

Neuron 4030 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: 7.6927. Min Range: -7.6927

Max Act: 7.6927. Min Act: -0.0001

Data Index: 487855 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.2796. Min Act: -0.0001

Data Index: 793814 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.4299. Min Act: -0.0001

Data Index: 149819 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.1234. Min Act: -0.0000

Data Index: 254381 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.2449. Min Act: -0.0001

Data Index: 67073 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.2415. Min Act: -0.0001

Data Index: 272120 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.0285. Min Act: -0.0001

Data Index: 421637 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.0397. Min Act: -0.0000

Data Index: 273298 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.1483. Min Act: -0.0001

Data Index: 78768 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.0167. Min Act: -0.0001

Data Index: 1108356 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.0931. Min Act: -0.0001

Data Index: 219396 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.9175. Min Act: -0.0001

Data Index: 1297332 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.8505. Min Act: -0.0001

Data Index: 567090 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.9357. Min Act: -0.0001

Data Index: 890435 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.9234. Min Act: -0.0001

Data Index: 653917 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.7249. Min Act: -0.0001

Data Index: 322382 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 7.6927. Min Range: -7.6927

Max Act: 7.0591. Min Act: -0.0001

Data Index: 647070 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.6867. Min Act: -0.0001

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.6588. Min Act: -0.0001

Data Index: 1158972 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 7.6927. Min Range: -7.6927

Max Act: 6.8193. Min Act: -0.0001

Data Index: 980998 (C4 (Web Text))

Max Activating Token Index: 507