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

Dataset: The Pile

Neuron 2179 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: 1.0270. Min Range: -1.0270

Max Act: 1.0270. Min Act: -0.0000

Data Index: 255060 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9930. Min Act: -0.0000

Data Index: 463725 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1602896 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9587. Min Act: -0.0000

Data Index: 769836 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 1.0270. Min Range: -1.0270

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1860233 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9857. Min Act: -0.0000

Data Index: 496822 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1191586 (The Pile)

Max Activating Token Index: 571

Text #7

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9719. Min Act: -0.0000

Data Index: 447729 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1236008 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9282. Min Act: -0.0000

Data Index: 848105 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9343. Min Act: -0.0000

Data Index: 508262 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9243. Min Act: -0.0000

Data Index: 569568 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1029449 (The Pile)

Max Activating Token Index: 248

Text #13

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1404419 (The Pile)

Max Activating Token Index: 261

Text #14

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9136. Min Act: -0.0000

Data Index: 945078 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9124. Min Act: -0.0000

Data Index: 261237 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9553. Min Act: -0.0000

Data Index: 38015 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1488937 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.9578. Min Act: -0.0000

Data Index: 870410 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 1.0270. Min Range: -1.0270

Max Act: 0.8605. Min Act: -0.0000

Data Index: 496005 (The Pile)

Max Activating Token Index: 530