Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1744 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0442. Min Act: -0.0005

Data Index: 462638 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0438. Min Act: -0.0005

Data Index: 979307 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0005

Data Index: 1267866 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0442. Min Act: -0.0005

Data Index: 86026 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0431. Min Act: -0.0005

Data Index: 383101 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0440. Min Act: -0.0005

Data Index: 770862 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0428. Min Act: -0.0005

Data Index: 191640 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0429. Min Act: -0.0005

Data Index: 49263 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0426. Min Act: -0.0005

Data Index: 862076 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0418. Min Act: -0.0005

Data Index: 275199 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0414. Min Act: -0.0005

Data Index: 721074 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0408. Min Act: -0.0005

Data Index: 660937 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1232120 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0405. Min Act: -0.0005

Data Index: 1187813 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0419. Min Act: -0.0005

Data Index: 103160 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0403. Min Act: -0.0005

Data Index: 629132 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0407. Min Act: -0.0005

Data Index: 439881 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0005

Data Index: 341598 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0390. Min Act: -0.0005

Data Index: 250000 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0404. Min Act: -0.0005

Data Index: 1131636 (C4 (Web Text))

Max Activating Token Index: 422