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

Dataset: The Pile

Neuron 456 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1045006 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5230. Min Act: -0.0000

Data Index: 115111 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1394096 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4756. Min Act: -0.0000

Data Index: 641606 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4832. Min Act: -0.0000

Data Index: 531845 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1467603 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4552. Min Act: 0.0000

Data Index: 215599 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4030. Min Act: -0.0000

Data Index: 900624 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1597527 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1050977 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1534271 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1571038 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1583176 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1096660 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3185. Min Act: -0.0000

Data Index: 338672 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1430224 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3385. Min Act: -0.0000

Data Index: 132259 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1369733 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1916848 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3375. Min Act: -0.0000

Data Index: 684377 (The Pile)

Max Activating Token Index: 687