Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1518 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1749. Min Range: -1.1749

Max Act: 1.1749. Min Act: -0.0001

Data Index: 209697 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.9963. Min Act: -0.0001

Data Index: 470036 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.1749. Min Range: -1.1749

Max Act: 1.0783. Min Act: -0.0001

Data Index: 1121698 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.8299. Min Act: -0.0001

Data Index: 934180 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.9319. Min Act: -0.0001

Data Index: 174596 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.8482. Min Act: -0.0001

Data Index: 360861 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.8305. Min Act: -0.0001

Data Index: 283993 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.8643. Min Act: -0.0001

Data Index: 850670 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.6214. Min Act: -0.0001

Data Index: 1199896 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.7550. Min Act: -0.0001

Data Index: 454131 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.7326. Min Act: -0.0001

Data Index: 413914 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.7406. Min Act: -0.0001

Data Index: 1238358 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.7826. Min Act: -0.0001

Data Index: 1295055 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.7029. Min Act: -0.0001

Data Index: 228492 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.7140. Min Act: -0.0001

Data Index: 1195760 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.6885. Min Act: -0.0001

Data Index: 382165 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.8352. Min Act: -0.0001

Data Index: 802541 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.6070. Min Act: -0.0001

Data Index: 240498 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.8112. Min Act: -0.0001

Data Index: 70572 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.1749. Min Range: -1.1749

Max Act: 0.7565. Min Act: -0.0001

Data Index: 483403 (C4 (Web Text))

Max Activating Token Index: 692