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

Dataset: The Pile

Neuron 1841 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1192041 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3963. Min Act: -0.0000

Data Index: 631396 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1557338 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3437. Min Act: -0.0000

Data Index: 808471 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1894908 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3319. Min Act: -0.0000

Data Index: 907146 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3044. Min Act: 0.0000

Data Index: 1872019 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3241. Min Act: -0.0000

Data Index: 996293 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1330419 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3322. Min Act: -0.0000

Data Index: 689344 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1211000 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3261. Min Act: -0.0000

Data Index: 28201 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.2859. Min Act: -0.0000

Data Index: 881392 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3013. Min Act: -0.0000

Data Index: 992138 (The Pile)

Max Activating Token Index: 966

Text #14

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1439870 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3045. Min Act: 0.0000

Data Index: 1427239 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.2926. Min Act: 0.0000

Data Index: 29920 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.3085. Min Act: -0.0000

Data Index: 625259 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.2973. Min Act: 0.0000

Data Index: 1055462 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 0.4364. Min Range: -0.4364

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1051905 (The Pile)

Max Activating Token Index: 288