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

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

Neuron 1830 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.6178. Min Act: -0.0001

Data Index: 453625 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.6081. Min Act: -0.0001

Data Index: 1596432 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.4106. Min Act: -0.0001

Data Index: 17084 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.3170. Min Act: -0.0001

Data Index: 875147 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.2876. Min Act: -0.0001

Data Index: 1199110 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.2639. Min Act: -0.0001

Data Index: 1638786 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.2596. Min Act: -0.0001

Data Index: 887062 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.2147. Min Act: -0.0001

Data Index: 161404 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.1526. Min Act: -0.0001

Data Index: 1259030 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.1337. Min Act: -0.0001

Data Index: 786431 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.1054. Min Act: -0.0001

Data Index: 691178 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.0977. Min Act: -0.0001

Data Index: 311051 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.0571. Min Act: -0.0001

Data Index: 320280 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.1765. Min Act: -0.0001

Data Index: 1103783 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.1129. Min Act: -0.0001

Data Index: 798669 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.0764. Min Act: -0.0001

Data Index: 729433 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.6178. Min Range: -1.6178

Max Act: 0.9946. Min Act: -0.0001

Data Index: 20173 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.0571. Min Act: -0.0001

Data Index: 360325 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.1309. Min Act: -0.0001

Data Index: 362099 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 1.6178. Min Range: -1.6178

Max Act: 1.0569. Min Act: -0.0001

Data Index: 848272 (C4 (Web Text))

Max Activating Token Index: 147