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

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

Neuron 109 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.1273. Min Act: -0.0000

Data Index: 707048 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.1273. Min Range: -1.1273

Max Act: 1.0646. Min Act: -0.0000

Data Index: 383836 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1021280 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9747. Min Act: -0.0000

Data Index: 461022 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1031777 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.9845. Min Act: -0.0000

Data Index: 513005 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8350. Min Act: -0.0000

Data Index: 719390 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1152629 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1083110 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8333. Min Act: -0.0000

Data Index: 503027 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8266. Min Act: -0.0000

Data Index: 947245 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8512. Min Act: -0.0000

Data Index: 567173 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7775. Min Act: -0.0000

Data Index: 299525 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1101180 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8431. Min Act: -0.0000

Data Index: 362650 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8028. Min Act: -0.0000

Data Index: 296522 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7521. Min Act: -0.0000

Data Index: 920138 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1338605 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7760. Min Act: -0.0000

Data Index: 386157 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.1273. Min Range: -1.1273

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1170115 (C4 (Web Text))

Max Activating Token Index: 315