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

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

Neuron 3079 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5777. Min Range: -4.5777

Max Act: 4.5777. Min Act: -0.0000

Data Index: 639305 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.8031. Min Act: -0.0000

Data Index: 677913 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.8329. Min Act: -0.0000

Data Index: 1359711 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.8387. Min Act: -0.0000

Data Index: 185733 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6209. Min Act: -0.0000

Data Index: 1164160 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6311. Min Act: -0.0000

Data Index: 579528 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.7596. Min Act: -0.0000

Data Index: 711724 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6028. Min Act: -0.0000

Data Index: 454750 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6105. Min Act: -0.0000

Data Index: 1261190 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.7599. Min Act: -0.0000

Data Index: 170087 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.5597. Min Act: -0.0000

Data Index: 673587 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.5458. Min Act: -0.0000

Data Index: 971611 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.8404. Min Act: -0.0000

Data Index: 373968 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6698. Min Act: -0.0000

Data Index: 717934 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6657. Min Act: -0.0000

Data Index: 1208368 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6477. Min Act: -0.0000

Data Index: 508855 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.8262. Min Act: -0.0000

Data Index: 425131 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6194. Min Act: -0.0000

Data Index: 288986 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6376. Min Act: -0.0000

Data Index: 1291972 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 4.5777. Min Range: -4.5777

Max Act: 3.6334. Min Act: -0.0000

Data Index: 987051 (C4 (Web Text))

Max Activating Token Index: 583