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

Dataset: The Pile

Neuron 3567 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: 1.3304. Min Range: -1.3304

Max Act: 1.3181. Min Act: -0.0000

Data Index: 87346 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1625330 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.3304. Min Act: -0.0000

Data Index: 105851 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1238301 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.1182. Min Act: -0.0000

Data Index: 450914 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0131. Min Act: -0.0000

Data Index: 190624 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0928. Min Act: -0.0000

Data Index: 750667 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.1335. Min Act: -0.0000

Data Index: 198835 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1562092 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1607179 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.9248. Min Act: -0.0000

Data Index: 818797 (The Pile)

Max Activating Token Index: 497

Text #11

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1917860 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1306096 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.9574. Min Act: -0.0000

Data Index: 443628 (The Pile)

Max Activating Token Index: 430

Text #14

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0994. Min Act: -0.0000

Data Index: 779206 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1353003 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1390999 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 1.3304. Min Range: -1.3304

Max Act: 1.0637. Min Act: -0.0000

Data Index: 33548 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1949534 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 1.3304. Min Range: -1.3304

Max Act: 0.9949. Min Act: -0.0000

Data Index: 297940 (The Pile)

Max Activating Token Index: 217