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

Dataset: The Pile

Neuron 1840 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1497. Min Range: -3.1497

Max Act: 3.1497. Min Act: 0.0000

Data Index: 944613 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 3.1497. Min Range: -3.1497

Max Act: 3.0612. Min Act: -0.0000

Data Index: 592549 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 3.1497. Min Range: -3.1497

Max Act: 3.0178. Min Act: -0.0000

Data Index: 1721627 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 3.1497. Min Range: -3.1497

Max Act: 3.0070. Min Act: -0.0000

Data Index: 912685 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.8220. Min Act: -0.0000

Data Index: 1723923 (The Pile)

Max Activating Token Index: 367

Text #5

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.6500. Min Act: -0.0000

Data Index: 288175 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.5187. Min Act: -0.0000

Data Index: 661590 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.5809. Min Act: -0.0000

Data Index: 1590030 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.4410. Min Act: -0.0000

Data Index: 1221801 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.4083. Min Act: -0.0000

Data Index: 1055727 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.1554. Min Act: -0.0000

Data Index: 1356341 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.6469. Min Act: -0.0000

Data Index: 398180 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.3466. Min Act: -0.0000

Data Index: 365374 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.1916. Min Act: -0.0000

Data Index: 141405 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.2820. Min Act: -0.0000

Data Index: 1048681 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.1608. Min Act: -0.0000

Data Index: 212985 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.1485. Min Act: -0.0000

Data Index: 717269 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.1328. Min Act: 0.0000

Data Index: 1316271 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 3.1497. Min Range: -3.1497

Max Act: 2.1069. Min Act: -0.0000

Data Index: 1997805 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 3.1497. Min Range: -3.1497

Max Act: 1.9900. Min Act: -0.0000

Data Index: 1250517 (The Pile)

Max Activating Token Index: 983