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

Dataset: The Pile

Neuron 1197 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1810092 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2906. Min Act: -0.0000

Data Index: 925509 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.3315. Min Act: -0.0000

Data Index: 400411 (The Pile)

Max Activating Token Index: 448

Text #3

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2447. Min Act: -0.0000

Data Index: 829752 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.3250. Min Act: -0.0000

Data Index: 604254 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2367. Min Act: -0.0000

Data Index: 159385 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2145. Min Act: -0.0000

Data Index: 399089 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1607412 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1421830 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1388. Min Act: -0.0000

Data Index: 538815 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1523785 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1239. Min Act: -0.0000

Data Index: 599311 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1231. Min Act: -0.0000

Data Index: 893200 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1283455 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1935866 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0597. Min Act: -0.0000

Data Index: 181130 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1185913 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1854432 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0167. Min Act: -0.0000

Data Index: 502927 (The Pile)

Max Activating Token Index: 77

Text #19

Max Range: 1.5278. Min Range: -1.5278

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1397187 (The Pile)

Max Activating Token Index: 865