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

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

Neuron 845 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1797. Min Range: -2.1797

Max Act: 2.1797. Min Act: -0.0000

Data Index: 819103 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 2.1797. Min Range: -2.1797

Max Act: 2.1119. Min Act: -0.0000

Data Index: 995346 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 2.1797. Min Range: -2.1797

Max Act: 2.0490. Min Act: -0.0000

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.9950. Min Act: -0.0000

Data Index: 1222150 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 2.1797. Min Range: -2.1797

Max Act: 2.0097. Min Act: -0.0000

Data Index: 31394 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 2.1797. Min Range: -2.1797

Max Act: 2.0399. Min Act: -0.0000

Data Index: 857215 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.8695. Min Act: -0.0000

Data Index: 1018786 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.8661. Min Act: -0.0000

Data Index: 480897 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.7412. Min Act: -0.0000

Data Index: 730696 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.8760. Min Act: -0.0000

Data Index: 312275 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.6828. Min Act: 0.0002

Data Index: 360632 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.8435. Min Act: -0.0000

Data Index: 1312996 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.6170. Min Act: -0.0000

Data Index: 48198 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.7335. Min Act: 0.0000

Data Index: 934991 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1235768 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.4397. Min Act: -0.0000

Data Index: 608135 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.5542. Min Act: 0.0000

Data Index: 721808 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.4814. Min Act: -0.0000

Data Index: 303838 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.3604. Min Act: -0.0000

Data Index: 373215 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 2.1797. Min Range: -2.1797

Max Act: 1.4213. Min Act: -0.0000

Data Index: 423123 (C4 (Web Text))

Max Activating Token Index: 611