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

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

Neuron 3507 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.4441. Min Act: -0.0000

Data Index: 840653 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1589. Min Act: -0.0000

Data Index: 165710 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0879. Min Act: -0.0000

Data Index: 407150 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0600. Min Act: -0.0000

Data Index: 980051 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0787. Min Act: -0.0000

Data Index: 413436 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0004. Min Act: -0.0000

Data Index: 211378 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.0210. Min Act: -0.0000

Data Index: 1461010 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9728. Min Act: -0.0000

Data Index: 975567 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9500. Min Act: 0.0000

Data Index: 1176429 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9566. Min Act: -0.0000

Data Index: 496320 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9451. Min Act: 0.0000

Data Index: 1125736 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1172466 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9077. Min Act: -0.0000

Data Index: 191403 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1193710 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1096626 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9156. Min Act: -0.0000

Data Index: 821307 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.8749. Min Act: 0.0000

Data Index: 737810 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.8668. Min Act: -0.0000

Data Index: 729642 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.8478. Min Act: -0.0000

Data Index: 631397 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.4441. Min Range: -1.4441

Max Act: 0.9047. Min Act: -0.0000

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 76