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

Dataset: The Pile

Neuron 1297 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: 3.8352. Min Range: -3.8352

Max Act: 3.8352. Min Act: -0.0000

Data Index: 1071022 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.8170. Min Act: -0.0000

Data Index: 908730 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.7670. Min Act: -0.0000

Data Index: 997373 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.2454. Min Act: -0.0000

Data Index: 940735 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.3570. Min Act: -0.0000

Data Index: 723567 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.2690. Min Act: -0.0000

Data Index: 1446118 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.2592. Min Act: -0.0000

Data Index: 28880 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.2333. Min Act: -0.0000

Data Index: 1761786 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.2001. Min Act: -0.0000

Data Index: 607279 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.1583. Min Act: -0.0000

Data Index: 296333 (The Pile)

Max Activating Token Index: 615

Text #10

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.1338. Min Act: -0.0000

Data Index: 530241 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.0081. Min Act: -0.0000

Data Index: 796535 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.1587. Min Act: -0.0000

Data Index: 1226600 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.0236. Min Act: -0.0000

Data Index: 446774 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.0028. Min Act: -0.0000

Data Index: 1459507 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 3.8352. Min Range: -3.8352

Max Act: 2.8374. Min Act: -0.0000

Data Index: 1819118 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 3.8352. Min Range: -3.8352

Max Act: 2.9444. Min Act: -0.0000

Data Index: 231136 (The Pile)

Max Activating Token Index: 385

Text #17

Max Range: 3.8352. Min Range: -3.8352

Max Act: 2.9052. Min Act: -0.0000

Data Index: 103157 (The Pile)

Max Activating Token Index: 688

Text #18

Max Range: 3.8352. Min Range: -3.8352

Max Act: 3.0284. Min Act: -0.0000

Data Index: 514343 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 3.8352. Min Range: -3.8352

Max Act: 2.8635. Min Act: -0.0000

Data Index: 1085810 (The Pile)

Max Activating Token Index: 196