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

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

Neuron 2866 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.7278. Min Act: -0.0002

Data Index: 535240 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.7344. Min Act: -0.0002

Data Index: 155820 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.7236. Min Act: -0.0002

Data Index: 632171 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6897. Min Act: -0.0002

Data Index: 266731 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6772. Min Act: -0.0002

Data Index: 67020 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6934. Min Act: -0.0002

Data Index: 401435 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6710. Min Act: -0.0002

Data Index: 1331095 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6630. Min Act: -0.0002

Data Index: 1029625 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6593. Min Act: -0.0002

Data Index: 549429 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6488. Min Act: -0.0002

Data Index: 164553 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6631. Min Act: -0.0002

Data Index: 29529 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6567. Min Act: -0.0002

Data Index: 24283 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6565. Min Act: -0.0002

Data Index: 484516 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6538. Min Act: -0.0002

Data Index: 726161 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6468. Min Act: -0.0002

Data Index: 973912 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6543. Min Act: -0.0002

Data Index: 440907 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6514. Min Act: -0.0002

Data Index: 1081603 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6587. Min Act: -0.0002

Data Index: 19158 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6382. Min Act: -0.0002

Data Index: 677489 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.7344. Min Range: -0.7344

Max Act: 0.6511. Min Act: -0.0002

Data Index: 726902 (C4 (Web Text))

Max Activating Token Index: 791