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

Dataset: The Pile

Neuron 1140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1500756 (The Pile)

Max Activating Token Index: 416

Text #1

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1515. Min Act: 0.0000

Data Index: 1846105 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1705. Min Act: -0.0000

Data Index: 558136 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1440249 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1579. Min Act: -0.0000

Data Index: 734174 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1574. Min Act: -0.0000

Data Index: 344029 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1690. Min Act: -0.0000

Data Index: 400411 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1516025 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1496297 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1445. Min Act: 0.0000

Data Index: 485399 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1434. Min Act: -0.0000

Data Index: 888898 (The Pile)

Max Activating Token Index: 837

Text #11

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1283. Min Act: -0.0000

Data Index: 762819 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1499. Min Act: -0.0000

Data Index: 339600 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1131860 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1433. Min Act: -0.0000

Data Index: 20095 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1490. Min Act: -0.0000

Data Index: 757787 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1388. Min Act: -0.0000

Data Index: 796701 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1879811 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1397053 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.2163. Min Range: -0.2163

Max Act: 0.1347. Min Act: -0.0000

Data Index: 76805 (The Pile)

Max Activating Token Index: 863