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

Dataset: The Pile

Neuron 1141 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: 0.8206. Min Range: -0.8206

Max Act: 0.7452. Min Act: -0.0000

Data Index: 359559 (The Pile)

Max Activating Token Index: 886

Text #1

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7181. Min Act: -0.0000

Data Index: 270160 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1296500 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7351. Min Act: -0.0000

Data Index: 921647 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.8206. Min Act: -0.0000

Data Index: 652455 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1277372 (The Pile)

Max Activating Token Index: 775

Text #6

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7087. Min Act: -0.0000

Data Index: 191601 (The Pile)

Max Activating Token Index: 732

Text #7

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6708. Min Act: -0.0000

Data Index: 261551 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6593. Min Act: -0.0000

Data Index: 286844 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.7456. Min Act: -0.0000

Data Index: 547391 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6753. Min Act: -0.0000

Data Index: 822033 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1991092 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1581374 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5538. Min Act: -0.0000

Data Index: 336249 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5812. Min Act: -0.0000

Data Index: 921064 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1294868 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6131. Min Act: -0.0000

Data Index: 158561 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1180900 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.5941. Min Act: -0.0000

Data Index: 120756 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 0.8206. Min Range: -0.8206

Max Act: 0.6030. Min Act: -0.0000

Data Index: 137813 (The Pile)

Max Activating Token Index: 74