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

Dataset: The Pile

Neuron 1053 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: 1.2705. Min Range: -1.2705

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1751405 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1383690 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1699815 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0817. Min Act: 0.0000

Data Index: 412005 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.1561. Min Act: 0.0000

Data Index: 1438042 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1687846 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0160. Min Act: -0.0000

Data Index: 1643617 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0161. Min Act: -0.0000

Data Index: 888705 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0485. Min Act: -0.0000

Data Index: 938896 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1975532 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9381. Min Act: -0.0000

Data Index: 540957 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9216. Min Act: -0.0000

Data Index: 285356 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1087925 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.2705. Min Range: -1.2705

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1777394 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9324. Min Act: -0.0000

Data Index: 449646 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.8584. Min Act: 0.0000

Data Index: 614984 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.8994. Min Act: -0.0000

Data Index: 55088 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1955583 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.8550. Min Act: -0.0000

Data Index: 796594 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 1.2705. Min Range: -1.2705

Max Act: 0.7416. Min Act: -0.0000

Data Index: 20147 (The Pile)

Max Activating Token Index: 1021