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

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

Neuron 754 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4045. Min Range: -2.4045

Max Act: 2.4045. Min Act: -0.0000

Data Index: 851512 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 2.4045. Min Range: -2.4045

Max Act: 2.1841. Min Act: -0.0000

Data Index: 988348 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 2.4045. Min Range: -2.4045

Max Act: 2.2050. Min Act: -0.0000

Data Index: 1114417 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 2.4045. Min Range: -2.4045

Max Act: 2.1919. Min Act: -0.0000

Data Index: 371919 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 2.4045. Min Range: -2.4045

Max Act: 2.2655. Min Act: -0.0000

Data Index: 514827 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 2.4045. Min Range: -2.4045

Max Act: 2.1108. Min Act: -0.0000

Data Index: 452640 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 2.4045. Min Range: -2.4045

Max Act: 2.0778. Min Act: -0.0000

Data Index: 1039732 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.8076. Min Act: -0.0000

Data Index: 508940 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.8889. Min Act: -0.0000

Data Index: 487833 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.9432. Min Act: -0.0000

Data Index: 901700 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.8276. Min Act: -0.0000

Data Index: 940389 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.7348. Min Act: -0.0000

Data Index: 581716 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.8446. Min Act: -0.0000

Data Index: 763882 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.7403. Min Act: -0.0000

Data Index: 1067239 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.6377. Min Act: -0.0000

Data Index: 908409 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.6193. Min Act: -0.0000

Data Index: 348517 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.5900. Min Act: -0.0000

Data Index: 56984 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.3839. Min Act: -0.0000

Data Index: 930690 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.4576. Min Act: -0.0000

Data Index: 734108 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 2.4045. Min Range: -2.4045

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1187336 (C4 (Web Text))

Max Activating Token Index: 888