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

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

Neuron 4979 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9310. Min Range: -6.9310

Max Act: 6.6431. Min Act: -0.0000

Data Index: 482407 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 6.9310. Min Range: -6.9310

Max Act: 6.9310. Min Act: -0.0000

Data Index: 1288603 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 6.9310. Min Range: -6.9310

Max Act: 6.4720. Min Act: -0.0000

Data Index: 340957 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 6.9310. Min Range: -6.9310

Max Act: 6.6472. Min Act: -0.0000

Data Index: 265579 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 6.9310. Min Range: -6.9310

Max Act: 5.9558. Min Act: -0.0000

Data Index: 89233 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 6.9310. Min Range: -6.9310

Max Act: 6.1206. Min Act: -0.0000

Data Index: 882089 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 6.9310. Min Range: -6.9310

Max Act: 5.8736. Min Act: -0.0000

Data Index: 1071108 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 6.9310. Min Range: -6.9310

Max Act: 5.7552. Min Act: -0.0000

Data Index: 632934 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 6.9310. Min Range: -6.9310

Max Act: 5.2581. Min Act: -0.0000

Data Index: 238467 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.9825. Min Act: -0.0000

Data Index: 1147326 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.8168. Min Act: -0.0000

Data Index: 714957 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.6843. Min Act: -0.0000

Data Index: 2321 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.2917. Min Act: -0.0000

Data Index: 867548 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.0838. Min Act: -0.0000

Data Index: 1060818 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.0580. Min Act: -0.0000

Data Index: 586607 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.1382. Min Act: -0.0000

Data Index: 287843 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 6.9310. Min Range: -6.9310

Max Act: 4.1408. Min Act: -0.0000

Data Index: 73177 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 6.9310. Min Range: -6.9310

Max Act: 3.9397. Min Act: -0.0000

Data Index: 280927 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 6.9310. Min Range: -6.9310

Max Act: 3.8029. Min Act: -0.0000

Data Index: 1084319 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 6.9310. Min Range: -6.9310

Max Act: 3.9674. Min Act: -0.0000

Data Index: 451454 (C4 (Web Text))

Max Activating Token Index: 130