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

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

Neuron 5628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.9917. Min Act: -0.0000

Data Index: 92881 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.9369. Min Act: -0.0000

Data Index: 447690 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.9311. Min Act: -0.0000

Data Index: 605879 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7949. Min Act: -0.0000

Data Index: 615683 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1277246 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8277. Min Act: -0.0000

Data Index: 740502 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1163105 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8479. Min Act: -0.0000

Data Index: 940663 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1101478 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1351191 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7378. Min Act: -0.0000

Data Index: 108170 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7296. Min Act: -0.0000

Data Index: 170578 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7140. Min Act: -0.0000

Data Index: 750820 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7204. Min Act: -0.0000

Data Index: 144575 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1139545 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7015. Min Act: -0.0000

Data Index: 122222 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7249. Min Act: -0.0000

Data Index: 269713 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6740. Min Act: -0.0000

Data Index: 54762 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6534. Min Act: -0.0000

Data Index: 260864 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6473. Min Act: -0.0000

Data Index: 501788 (C4 (Web Text))

Max Activating Token Index: 863