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

Dataset: The Pile

Neuron 3453 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0263. Min Range: -1.0263

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1117335 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1952800 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.8333. Min Act: -0.0000

Data Index: 595035 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7664. Min Act: -0.0000

Data Index: 107683 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7876. Min Act: -0.0000

Data Index: 414921 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1318173 (The Pile)

Max Activating Token Index: 9

Text #6

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1587124 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7562. Min Act: -0.0000

Data Index: 418036 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1317241 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7164. Min Act: -0.0000

Data Index: 690742 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1039602 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6929. Min Act: -0.0000

Data Index: 47106 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1735215 (The Pile)

Max Activating Token Index: 144

Text #13

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1224053 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1415672 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1840027 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1859664 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6596. Min Act: -0.0000

Data Index: 736316 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6381. Min Act: -0.0000

Data Index: 861456 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 1.0263. Min Range: -1.0263

Max Act: 0.6808. Min Act: -0.0000

Data Index: 153989 (The Pile)

Max Activating Token Index: 212