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

Dataset: The Pile

Neuron 1977 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1259140 (The Pile)

Max Activating Token Index: 409

Text #1

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4058. Min Act: -0.0000

Data Index: 103429 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1527979 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3913. Min Act: 0.0000

Data Index: 1863359 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1655248 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1557057 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1098581 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3678. Min Act: -0.0000

Data Index: 535583 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3274. Min Act: -0.0000

Data Index: 852063 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1656387 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3899. Min Act: -0.0000

Data Index: 609794 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1291345 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1855758 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3470. Min Act: -0.0000

Data Index: 1336629 (The Pile)

Max Activating Token Index: 516

Text #14

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3366. Min Act: -0.0000

Data Index: 515602 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1716455 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3107. Min Act: -0.0000

Data Index: 830199 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1997229 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3533. Min Act: -0.0000

Data Index: 467031 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3090. Min Act: -0.0000

Data Index: 633653 (The Pile)

Max Activating Token Index: 63