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

Dataset: The Pile

Neuron 2094 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.9003. Min Act: -0.0000

Data Index: 1620243 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.7373. Min Act: -0.0000

Data Index: 1402955 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 7.0313. Min Range: -7.0313

Max Act: 7.0313. Min Act: -0.0000

Data Index: 1349981 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.5508. Min Act: -0.0000

Data Index: 1419884 (The Pile)

Max Activating Token Index: 555

Text #4

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.9512. Min Act: -0.0000

Data Index: 325723 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 7.0313. Min Range: -7.0313

Max Act: 5.8200. Min Act: -0.0000

Data Index: 807568 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.6422. Min Act: -0.0000

Data Index: 277160 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.5829. Min Act: -0.0000

Data Index: 607367 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.7150. Min Act: -0.0000

Data Index: 1387485 (The Pile)

Max Activating Token Index: 906

Text #9

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.3779. Min Act: -0.0000

Data Index: 1937931 (The Pile)

Max Activating Token Index: 16

Text #10

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.4702. Min Act: -0.0000

Data Index: 1629210 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.0779. Min Act: -0.0000

Data Index: 1711457 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.2393. Min Act: -0.0000

Data Index: 1606492 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.3662. Min Act: -0.0000

Data Index: 1832016 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.1523. Min Act: -0.0000

Data Index: 1960166 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 7.0313. Min Range: -7.0313

Max Act: 5.9942. Min Act: -0.0000

Data Index: 764654 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 7.0313. Min Range: -7.0313

Max Act: 5.9546. Min Act: -0.0000

Data Index: 1344964 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 7.0313. Min Range: -7.0313

Max Act: 5.9294. Min Act: -0.0000

Data Index: 500941 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.2818. Min Act: -0.0000

Data Index: 628521 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 7.0313. Min Range: -7.0313

Max Act: 6.6275. Min Act: -0.0000

Data Index: 275310 (The Pile)

Max Activating Token Index: 762