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

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

Neuron 4950 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.9201. Min Act: -0.0000

Data Index: 174119 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.7105. Min Act: -0.0000

Data Index: 1338537 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.6811. Min Act: -0.0000

Data Index: 1007747 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.7238. Min Act: -0.0000

Data Index: 684987 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.4893. Min Act: -0.0001

Data Index: 1138331 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.5567. Min Act: -0.0000

Data Index: 626054 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.4620. Min Act: -0.0000

Data Index: 1340120 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.1664. Min Act: -0.0000

Data Index: 390017 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.2864. Min Act: -0.0000

Data Index: 885781 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.7564. Min Act: -0.0000

Data Index: 546551 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.8192. Min Act: -0.0000

Data Index: 173405 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 4.9201. Min Range: -4.9201

Max Act: 4.1441. Min Act: -0.0000

Data Index: 200217 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.8693. Min Act: -0.0000

Data Index: 271233 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.6785. Min Act: -0.0000

Data Index: 511661 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.8466. Min Act: -0.0000

Data Index: 403271 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.9831. Min Act: -0.0000

Data Index: 927522 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.6593. Min Act: -0.0000

Data Index: 771577 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.7486. Min Act: -0.0000

Data Index: 254209 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.4254. Min Act: -0.0000

Data Index: 141352 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 4.9201. Min Range: -4.9201

Max Act: 3.5218. Min Act: -0.0000

Data Index: 1166734 (C4 (Web Text))

Max Activating Token Index: 621