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

Dataset: The Pile

Neuron 3204 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.4053. Min Act: -0.0000

Data Index: 528193 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.4045. Min Act: -0.0000

Data Index: 685788 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1654348 (The Pile)

Max Activating Token Index: 732

Text #3

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1008820 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3423. Min Act: -0.0000

Data Index: 842760 (The Pile)

Max Activating Token Index: 723

Text #5

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1488000 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1003860 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3391. Min Act: -0.0000

Data Index: 322303 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1075524 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1134317 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1553592 (The Pile)

Max Activating Token Index: 642

Text #11

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3548. Min Act: -0.0000

Data Index: 319529 (The Pile)

Max Activating Token Index: 671

Text #12

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1841555 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3262. Min Act: -0.0000

Data Index: 71312 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1751420 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3308. Min Act: 0.0000

Data Index: 78407 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3069. Min Act: -0.0000

Data Index: 223445 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3123. Min Act: -0.0000

Data Index: 642040 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2817. Min Act: -0.0000

Data Index: 134369 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3030. Min Act: 0.0000

Data Index: 1417733 (The Pile)

Max Activating Token Index: 506