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

Dataset: The Pile

Neuron 1813 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: 0.4089. Min Range: -0.4089

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1562000 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.4089. Min Act: -0.0000

Data Index: 586 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1986207 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3755. Min Act: -0.0000

Data Index: 829454 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2974. Min Act: -0.0000

Data Index: 718245 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1166304 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3033. Min Act: -0.0000

Data Index: 674473 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1659985 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1369231 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2375. Min Act: -0.0000

Data Index: 882495 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1788040 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1769858 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1268753 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1016447 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1816147 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1023581 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2393. Min Act: -0.0000

Data Index: 740623 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2405. Min Act: -0.0000

Data Index: 88918 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2269. Min Act: -0.0000

Data Index: 152277 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1206701 (The Pile)

Max Activating Token Index: 157