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

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

Neuron 2074 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1435. Min Range: -2.1435

Max Act: 2.1435. Min Act: -0.0000

Data Index: 319809 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.9007. Min Act: -0.0000

Data Index: 83587 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.8099. Min Act: -0.0000

Data Index: 527478 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.8145. Min Act: -0.0000

Data Index: 770959 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.7045. Min Act: -0.0000

Data Index: 43299 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1137991 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.7162. Min Act: -0.0000

Data Index: 662374 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6151. Min Act: -0.0000

Data Index: 957516 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6970. Min Act: -0.0000

Data Index: 26333 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6850. Min Act: -0.0000

Data Index: 658035 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.7517. Min Act: -0.0000

Data Index: 821066 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1138390 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6351. Min Act: -0.0000

Data Index: 303314 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6271. Min Act: -0.0000

Data Index: 220280 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.6306. Min Act: -0.0000

Data Index: 701607 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1146563 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.5938. Min Act: -0.0000

Data Index: 539238 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.5097. Min Act: -0.0000

Data Index: 662311 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.5155. Min Act: -0.0000

Data Index: 411892 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 2.1435. Min Range: -2.1435

Max Act: 1.4121. Min Act: -0.0000

Data Index: 659601 (C4 (Web Text))

Max Activating Token Index: 87