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

Dataset: The Pile

Neuron 1413 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: 0.4936. Min Range: -0.4936

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1312449 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4936. Min Act: -0.0000

Data Index: 427146 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1197238 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3905. Min Act: -0.0000

Data Index: 150081 (The Pile)

Max Activating Token Index: 633

Text #4

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1293438 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1658599 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4215. Min Act: -0.0000

Data Index: 415588 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1415049 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1822706 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3554. Min Act: -0.0000

Data Index: 1329164 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3782. Min Act: -0.0000

Data Index: 499132 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3759. Min Act: -0.0000

Data Index: 965053 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.4128. Min Act: -0.0000

Data Index: 781244 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3903. Min Act: -0.0000

Data Index: 930676 (The Pile)

Max Activating Token Index: 534

Text #14

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3936. Min Act: -0.0000

Data Index: 765162 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1751410 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3654. Min Act: -0.0000

Data Index: 608981 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3447. Min Act: -0.0000

Data Index: 456050 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1307275 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 0.4936. Min Range: -0.4936

Max Act: 0.3743. Min Act: -0.0000

Data Index: 822451 (The Pile)

Max Activating Token Index: 760