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

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

Neuron 5059 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.1020. Min Act: -0.0000

Data Index: 200843 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.0633. Min Act: -0.0000

Data Index: 1339713 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1307468 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.0737. Min Act: -0.0000

Data Index: 814049 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.0289. Min Act: -0.0000

Data Index: 951251 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1161075 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 1.1020. Min Range: -1.1020

Max Act: 1.0438. Min Act: -0.0000

Data Index: 839353 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1172785 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1337244 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9589. Min Act: -0.0000

Data Index: 7255 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9290. Min Act: -0.0000

Data Index: 789385 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9737. Min Act: -0.0000

Data Index: 193762 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9053. Min Act: -0.0000

Data Index: 836740 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9291. Min Act: -0.0000

Data Index: 986933 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1298316 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9221. Min Act: -0.0000

Data Index: 286077 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1164116 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1047273 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9550. Min Act: -0.0000

Data Index: 782301 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 1.1020. Min Range: -1.1020

Max Act: 0.9078. Min Act: -0.0000

Data Index: 724481 (C4 (Web Text))

Max Activating Token Index: 834