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

Dataset: The Pile

Neuron 3538 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.3263. Min Act: 0.0000

Data Index: 1002304 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2904. Min Act: -0.0000

Data Index: 198359 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2889. Min Act: -0.0000

Data Index: 731765 (The Pile)

Max Activating Token Index: 920

Text #3

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2817. Min Act: -0.0000

Data Index: 708211 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1023768 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1050481 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1552556 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1172552 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1085712 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2563. Min Act: 0.0000

Data Index: 1004217 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2652. Min Act: -0.0000

Data Index: 64596 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2316. Min Act: -0.0000

Data Index: 423677 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2458. Min Act: -0.0000

Data Index: 978223 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1972935 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1422167 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1660699 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2495. Min Act: -0.0000

Data Index: 820776 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2521. Min Act: -0.0000

Data Index: 739455 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1732778 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1274195 (The Pile)

Max Activating Token Index: 746