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

Dataset: The Pile

Neuron 2894 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: 0.5699. Min Range: -0.5699

Max Act: 0.5699. Min Act: -0.0000

Data Index: 327620 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1582429 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.5216. Min Act: -0.0000

Data Index: 122602 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1531180 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4637. Min Act: -0.0000

Data Index: 605088 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1980907 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4641. Min Act: -0.0000

Data Index: 205625 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4125. Min Act: -0.0000

Data Index: 757877 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1745203 (The Pile)

Max Activating Token Index: 901

Text #9

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1631173 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4308. Min Act: -0.0000

Data Index: 99315 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1666166 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4268. Min Act: -0.0000

Data Index: 190200 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4221. Min Act: -0.0000

Data Index: 236560 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4508. Min Act: -0.0000

Data Index: 902805 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4207. Min Act: -0.0000

Data Index: 818358 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4449. Min Act: -0.0000

Data Index: 705971 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4241. Min Act: -0.0000

Data Index: 161635 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1537682 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 0.5699. Min Range: -0.5699

Max Act: 0.4510. Min Act: -0.0000

Data Index: 8153 (The Pile)

Max Activating Token Index: 276