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

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

Neuron 1618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.6955. Min Act: -0.0000

Data Index: 415960 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.5811. Min Act: -0.0000

Data Index: 405112 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.4278. Min Act: -0.0000

Data Index: 372072 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.4185. Min Act: -0.0000

Data Index: 897419 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.4464. Min Act: -0.0000

Data Index: 273988 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.4341. Min Act: -0.0000

Data Index: 58890 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.3307. Min Act: -0.0000

Data Index: 482602 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1251925 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2884. Min Act: -0.0000

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2889. Min Act: -0.0000

Data Index: 664336 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1329935 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1086246 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2286. Min Act: -0.0000

Data Index: 265875 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2845. Min Act: -0.0000

Data Index: 247069 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.1575. Min Act: -0.0000

Data Index: 749731 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1010194 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2326. Min Act: -0.0000

Data Index: 394074 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.1482. Min Act: -0.0000

Data Index: 822784 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1355819 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 1.6955. Min Range: -1.6955

Max Act: 1.2601. Min Act: -0.0000

Data Index: 315981 (C4 (Web Text))

Max Activating Token Index: 361