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

Dataset: The Pile

Neuron 1762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1615698 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0877. Min Act: -0.0000

Data Index: 18709 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1838357 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1266098 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0318. Min Act: -0.0000

Data Index: 10478 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0448. Min Act: -0.0000

Data Index: 639963 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1352455 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1578185 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1190731 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.8241. Min Act: -0.0000

Data Index: 257578 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1881949 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1281677 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1364694 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1157116 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1467176 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1588329 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7075. Min Act: -0.0000

Data Index: 529562 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.6994. Min Act: -0.0000

Data Index: 39199 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7108. Min Act: -0.0000

Data Index: 71059 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1750366 (The Pile)

Max Activating Token Index: 818