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

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

Neuron 3812 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: 0.8186. Min Range: -0.8186

Max Act: 0.8186. Min Act: -0.0000

Data Index: 830150 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1609682 (Python Code)

Max Activating Token Index: 679

Text #2

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7697. Min Act: -0.0000

Data Index: 928430 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6830. Min Act: -0.0000

Data Index: 94980 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7250. Min Act: -0.0000

Data Index: 455384 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.7025. Min Act: 0.0001

Data Index: 87580 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1371196 (Python Code)

Max Activating Token Index: 835

Text #7

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1601835 (Python Code)

Max Activating Token Index: 987

Text #8

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5914. Min Act: -0.0000

Data Index: 824372 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5978. Min Act: -0.0000

Data Index: 551448 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1418080 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5504. Min Act: -0.0000

Data Index: 625551 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5848. Min Act: -0.0000

Data Index: 518955 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5231. Min Act: -0.0000

Data Index: 949538 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5765. Min Act: -0.0000

Data Index: 766939 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5456. Min Act: -0.0000

Data Index: 670034 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1276643 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1390424 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.5177. Min Act: -0.0000

Data Index: 986588 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.8186. Min Range: -0.8186

Max Act: 0.4833. Min Act: -0.0000

Data Index: 991829 (C4 (Web Text))

Max Activating Token Index: 925