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

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

Neuron 5077 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.9485. Min Act: -0.0001

Data Index: 1214438 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1334184 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7154. Min Act: -0.0001

Data Index: 49519 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7612. Min Act: -0.0001

Data Index: 49343 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7032. Min Act: -0.0001

Data Index: 901501 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7030. Min Act: -0.0001

Data Index: 1001330 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6926. Min Act: -0.0001

Data Index: 852802 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7184. Min Act: -0.0001

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1357725 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6508. Min Act: -0.0001

Data Index: 976651 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6841. Min Act: -0.0001

Data Index: 828193 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6524. Min Act: -0.0001

Data Index: 211030 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7167. Min Act: -0.0001

Data Index: 291961 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.7477. Min Act: -0.0001

Data Index: 277915 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.5968. Min Act: -0.0001

Data Index: 315239 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.5696. Min Act: -0.0001

Data Index: 804709 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6373. Min Act: -0.0001

Data Index: 751564 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6070. Min Act: -0.0001

Data Index: 908612 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.5515. Min Act: -0.0001

Data Index: 348010 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.9485. Min Range: -0.9485

Max Act: 0.6203. Min Act: -0.0001

Data Index: 1266913 (C4 (Web Text))

Max Activating Token Index: 692