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

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

Neuron 1244 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1334043 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2655. Min Act: -0.0000

Data Index: 503450 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2546. Min Act: -0.0001

Data Index: 193493 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2335. Min Act: -0.0001

Data Index: 318244 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2323. Min Act: -0.0000

Data Index: 848496 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2243. Min Act: -0.0001

Data Index: 942288 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2314. Min Act: -0.0001

Data Index: 887666 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2239. Min Act: -0.0001

Data Index: 1303524 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1273705 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2126. Min Act: -0.0000

Data Index: 525201 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2119. Min Act: -0.0000

Data Index: 665129 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2121. Min Act: -0.0001

Data Index: 485339 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2018. Min Act: -0.0000

Data Index: 465938 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2087. Min Act: -0.0000

Data Index: 619662 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1096883 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2000. Min Act: -0.0000

Data Index: 114156 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1987. Min Act: -0.0000

Data Index: 556619 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1962. Min Act: -0.0001

Data Index: 672302 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1841. Min Act: -0.0000

Data Index: 851511 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1865. Min Act: -0.0000

Data Index: 738020 (C4 (Web Text))

Max Activating Token Index: 469