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

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

Neuron 4566 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9458. Min Act: -0.0001

Data Index: 1068275 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9924. Min Act: -0.0001

Data Index: 484808 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8769. Min Act: -0.0001

Data Index: 337002 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8280. Min Act: -0.0001

Data Index: 242540 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8956. Min Act: -0.0001

Data Index: 269614 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8115. Min Act: -0.0001

Data Index: 570535 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8491. Min Act: -0.0001

Data Index: 1314515 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8636. Min Act: -0.0001

Data Index: 245003 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8189. Min Act: -0.0001

Data Index: 36062 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8329. Min Act: -0.0000

Data Index: 866233 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8455. Min Act: -0.0001

Data Index: 592743 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8565. Min Act: -0.0001

Data Index: 256323 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.7694. Min Act: -0.0000

Data Index: 467379 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8103. Min Act: -0.0001

Data Index: 441566 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8088. Min Act: -0.0001

Data Index: 913046 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1356529 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8365. Min Act: -0.0000

Data Index: 909701 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8672. Min Act: -0.0001

Data Index: 230112 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8514. Min Act: -0.0001

Data Index: 1219626 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.7638. Min Act: -0.0001

Data Index: 938008 (C4 (Web Text))

Max Activating Token Index: 167