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

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

Neuron 4075 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9633. Min Range: -6.9633

Max Act: 6.9633. Min Act: -0.0000

Data Index: 132282 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 6.9633. Min Range: -6.9633

Max Act: 6.5652. Min Act: -0.0000

Data Index: 1247274 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 6.9633. Min Range: -6.9633

Max Act: 6.5000. Min Act: -0.0000

Data Index: 975304 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.3719. Min Act: -0.0000

Data Index: 672235 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.9035. Min Act: 0.0000

Data Index: 144371 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.8930. Min Act: -0.0000

Data Index: 917995 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.6735. Min Act: -0.0000

Data Index: 168001 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.7898. Min Act: -0.0000

Data Index: 1028159 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.5587. Min Act: -0.0000

Data Index: 708294 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.5205. Min Act: -0.0000

Data Index: 699150 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.8748. Min Act: -0.0000

Data Index: 124463 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.6380. Min Act: -0.0000

Data Index: 130097 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.5988. Min Act: 0.0000

Data Index: 818528 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.9738. Min Act: -0.0000

Data Index: 220566 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.5737. Min Act: -0.0000

Data Index: 522583 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.1511. Min Act: 0.0000

Data Index: 800868 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.3049. Min Act: 0.0000

Data Index: 150177 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.2700. Min Act: -0.0000

Data Index: 385185 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.2821. Min Act: -0.0000

Data Index: 438032 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 6.9633. Min Range: -6.9633

Max Act: 5.2126. Min Act: 0.0000

Data Index: 546724 (C4 (Web Text))

Max Activating Token Index: 972