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

Dataset: The Pile

Neuron 3644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1140945 (The Pile)

Max Activating Token Index: 372

Text #1

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1868. Min Act: -0.0000

Data Index: 550587 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1586. Min Act: -0.0000

Data Index: 306293 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1701161 (The Pile)

Max Activating Token Index: 994

Text #4

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1311137 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1806897 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1096183 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1352. Min Act: -0.0000

Data Index: 654537 (The Pile)

Max Activating Token Index: 201

Text #8

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1442. Min Act: -0.0000

Data Index: 391642 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1337. Min Act: -0.0000

Data Index: 46573 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1319. Min Act: -0.0000

Data Index: 585736 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1181. Min Act: -0.0000

Data Index: 869912 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1614377 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1258. Min Act: -0.0000

Data Index: 978805 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1326. Min Act: -0.0000

Data Index: 321223 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1191. Min Act: -0.0000

Data Index: 171359 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1225. Min Act: -0.0000

Data Index: 423054 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1535204 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1173. Min Act: -0.0000

Data Index: 291972 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1176. Min Act: -0.0000

Data Index: 143052 (The Pile)

Max Activating Token Index: 112