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

Dataset: The Pile

Neuron 1935 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: 8.3925. Min Range: -8.3925

Max Act: 8.3925. Min Act: -0.0000

Data Index: 425409 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 8.3925. Min Range: -8.3925

Max Act: 7.3439. Min Act: -0.0000

Data Index: 1136414 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 8.3925. Min Range: -8.3925

Max Act: 4.6246. Min Act: -0.0000

Data Index: 1175482 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.6582. Min Act: -0.0000

Data Index: 1281566 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.6211. Min Act: -0.0000

Data Index: 74675 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.5031. Min Act: -0.0000

Data Index: 1953145 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.7730. Min Act: -0.0000

Data Index: 1519793 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.3502. Min Act: -0.0000

Data Index: 1182290 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.3157. Min Act: -0.0000

Data Index: 1401902 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.7704. Min Act: -0.0000

Data Index: 1760505 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.6437. Min Act: -0.0000

Data Index: 1300481 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.2659. Min Act: -0.0000

Data Index: 1819870 (The Pile)

Max Activating Token Index: 359

Text #12

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.5786. Min Act: -0.0000

Data Index: 1114552 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.4228. Min Act: -0.0000

Data Index: 1546919 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 8.3925. Min Range: -8.3925

Max Act: 2.9668. Min Act: -0.0000

Data Index: 12163 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.2539. Min Act: -0.0000

Data Index: 1858404 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.5388. Min Act: -0.0000

Data Index: 1788609 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.4752. Min Act: -0.0000

Data Index: 1968162 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.3560. Min Act: -0.0000

Data Index: 1387147 (The Pile)

Max Activating Token Index: 451

Text #19

Max Range: 8.3925. Min Range: -8.3925

Max Act: 3.1794. Min Act: -0.0000

Data Index: 819755 (The Pile)

Max Activating Token Index: 960