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

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

Neuron 4859 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.5951. Min Act: 0.0000

Data Index: 56294 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1336089 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.4149. Min Act: -0.0000

Data Index: 531404 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1216032 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.3619. Min Act: 0.0000

Data Index: 685332 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2612. Min Act: -0.0000

Data Index: 304793 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.3143. Min Act: 0.0000

Data Index: 939048 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1236012 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2232. Min Act: -0.0000

Data Index: 89223 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2760. Min Act: -0.0000

Data Index: 765889 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2477. Min Act: -0.0000

Data Index: 346095 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2392. Min Act: -0.0000

Data Index: 581462 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2303. Min Act: -0.0000

Data Index: 791057 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2341. Min Act: 0.0000

Data Index: 977972 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1112811 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.1978. Min Act: 0.0000

Data Index: 558667 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.1879. Min Act: -0.0000

Data Index: 785453 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.1899. Min Act: 0.0000

Data Index: 267737 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.1893. Min Act: -0.0000

Data Index: 816102 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 1.5951. Min Range: -1.5951

Max Act: 1.1721. Min Act: -0.0000

Data Index: 640970 (C4 (Web Text))

Max Activating Token Index: 347