Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1069 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4601. Min Act: -0.0001

Data Index: 1290812 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4557. Min Act: -0.0001

Data Index: 341585 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4106. Min Act: -0.0001

Data Index: 193754 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4070. Min Act: -0.0001

Data Index: 1288597 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3505. Min Act: -0.0001

Data Index: 389732 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4927. Min Act: -0.0001

Data Index: 1184641 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3010. Min Act: -0.0001

Data Index: 1076163 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.3376. Min Act: -0.0001

Data Index: 1357650 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.4157. Min Act: -0.0001

Data Index: 1061754 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2697. Min Act: -0.0001

Data Index: 113446 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2709. Min Act: -0.0001

Data Index: 843232 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2451. Min Act: -0.0001

Data Index: 414280 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2290. Min Act: -0.0001

Data Index: 693589 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.1895. Min Act: -0.0001

Data Index: 40148 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2302. Min Act: -0.0001

Data Index: 763226 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2922. Min Act: -0.0001

Data Index: 1052535 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2400. Min Act: -0.0001

Data Index: 964975 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2129. Min Act: -0.0001

Data Index: 1019832 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2341. Min Act: -0.0001

Data Index: 1054031 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.4927. Min Range: -1.4927

Max Act: 1.2335. Min Act: -0.0001

Data Index: 272598 (C4 (Web Text))

Max Activating Token Index: 408