Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5080 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4462. Min Range: -4.4462

Max Act: 4.4462. Min Act: -0.0000

Data Index: 661291 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 4.4462. Min Range: -4.4462

Max Act: 3.9439. Min Act: -0.0000

Data Index: 1067711 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 4.4462. Min Range: -4.4462

Max Act: 4.1640. Min Act: -0.0000

Data Index: 434402 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 4.4462. Min Range: -4.4462

Max Act: 3.7604. Min Act: -0.0000

Data Index: 785836 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 4.4462. Min Range: -4.4462

Max Act: 3.9411. Min Act: -0.0000

Data Index: 161748 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 4.4462. Min Range: -4.4462

Max Act: 3.3384. Min Act: -0.0000

Data Index: 741444 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.9839. Min Act: -0.0000

Data Index: 288060 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.7270. Min Act: -0.0000

Data Index: 317407 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.1323. Min Act: -0.0000

Data Index: 490588 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.1900. Min Act: -0.0000

Data Index: 634808 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.2156. Min Act: -0.0000

Data Index: 959364 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.0476. Min Act: -0.0000

Data Index: 278387 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.0897. Min Act: -0.0000

Data Index: 768934 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 4.4462. Min Range: -4.4462

Max Act: 1.9722. Min Act: -0.0001

Data Index: 96994 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 4.4462. Min Range: -4.4462

Max Act: 1.9930. Min Act: -0.0000

Data Index: 199946 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 4.4462. Min Range: -4.4462

Max Act: 1.9916. Min Act: -0.0000

Data Index: 574375 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 4.4462. Min Range: -4.4462

Max Act: 1.7658. Min Act: -0.0000

Data Index: 187104 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 4.4462. Min Range: -4.4462

Max Act: 2.0013. Min Act: -0.0000

Data Index: 421294 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 4.4462. Min Range: -4.4462

Max Act: 1.8279. Min Act: -0.0000

Data Index: 1156565 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 4.4462. Min Range: -4.4462

Max Act: 1.7207. Min Act: -0.0000

Data Index: 1198844 (C4 (Web Text))

Max Activating Token Index: 732