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

Dataset: The Pile

Neuron 4885 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5319. Min Range: -7.5319

Max Act: 7.0771. Min Act: -0.0000

Data Index: 1255994 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 7.5319. Min Range: -7.5319

Max Act: 7.0426. Min Act: -0.0000

Data Index: 713646 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.9095. Min Act: -0.0000

Data Index: 783385 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 7.5319. Min Range: -7.5319

Max Act: 7.5319. Min Act: -0.0000

Data Index: 878606 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 7.5319. Min Range: -7.5319

Max Act: 7.5234. Min Act: -0.0000

Data Index: 835282 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.9696. Min Act: -0.0000

Data Index: 892809 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.8263. Min Act: -0.0000

Data Index: 341300 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.3984. Min Act: -0.0000

Data Index: 1483538 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.7382. Min Act: -0.0000

Data Index: 958760 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.9434. Min Act: -0.0000

Data Index: 164394 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.5045. Min Act: -0.0000

Data Index: 175265 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.6426. Min Act: -0.0000

Data Index: 986824 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.3315. Min Act: -0.0000

Data Index: 910722 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.9395. Min Act: -0.0000

Data Index: 628021 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.6801. Min Act: -0.0000

Data Index: 1586842 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 7.5319. Min Range: -7.5319

Max Act: 7.0252. Min Act: -0.0000

Data Index: 1212163 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 7.5319. Min Range: -7.5319

Max Act: 5.9798. Min Act: -0.0000

Data Index: 438025 (The Pile)

Max Activating Token Index: 915

Text #17

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.3089. Min Act: -0.0000

Data Index: 375177 (The Pile)

Max Activating Token Index: 623

Text #18

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.4607. Min Act: -0.0000

Data Index: 388641 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 7.5319. Min Range: -7.5319

Max Act: 6.4214. Min Act: -0.0000

Data Index: 1135507 (The Pile)

Max Activating Token Index: 566