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

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

Neuron 425 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: 1.3428. Min Range: -1.3428

Max Act: 1.1444. Min Act: -0.0001

Data Index: 244738 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.1613. Min Act: -0.0001

Data Index: 328668 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.3428. Min Act: -0.0001

Data Index: 1102961 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.0718. Min Act: -0.0001

Data Index: 1214345 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.3428. Min Range: -1.3428

Max Act: 1.0161. Min Act: -0.0001

Data Index: 594709 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.9489. Min Act: -0.0001

Data Index: 1214009 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.8866. Min Act: -0.0001

Data Index: 1346468 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7826. Min Act: -0.0001

Data Index: 131916 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1140863 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7053. Min Act: -0.0001

Data Index: 635824 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.8152. Min Act: -0.0001

Data Index: 105596 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.8087. Min Act: -0.0001

Data Index: 761254 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.8021. Min Act: -0.0001

Data Index: 1055056 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7351. Min Act: -0.0001

Data Index: 981044 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7596. Min Act: -0.0001

Data Index: 282101 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7242. Min Act: -0.0001

Data Index: 503082 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7159. Min Act: -0.0001

Data Index: 602975 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7290. Min Act: -0.0001

Data Index: 1076298 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.6835. Min Act: -0.0001

Data Index: 800427 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.3428. Min Range: -1.3428

Max Act: 0.7315. Min Act: -0.0001

Data Index: 946201 (C4 (Web Text))

Max Activating Token Index: 204