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

Dataset: The Pile

Neuron 1067 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: 0.7314. Min Range: -0.7314

Max Act: 0.7314. Min Act: -0.0000

Data Index: 701389 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1647108 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.6136. Min Act: -0.0000

Data Index: 917545 (The Pile)

Max Activating Token Index: 730

Text #3

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1053054 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1165722 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1221308 (The Pile)

Max Activating Token Index: 594

Text #6

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5461. Min Act: -0.0000

Data Index: 452918 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5452. Min Act: -0.0000

Data Index: 87809 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1659036 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1139942 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1277443 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5303. Min Act: -0.0000

Data Index: 133584 (The Pile)

Max Activating Token Index: 877

Text #12

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1863160 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1237515 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1181551 (The Pile)

Max Activating Token Index: 299

Text #15

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1854189 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5211. Min Act: -0.0000

Data Index: 637669 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1763700 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.5435. Min Act: -0.0000

Data Index: 595442 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.7314. Min Range: -0.7314

Max Act: 0.4848. Min Act: -0.0000

Data Index: 672693 (The Pile)

Max Activating Token Index: 769