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

Dataset: The Pile

Neuron 1917 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1340120 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.7535. Min Act: -0.0000

Data Index: 697245 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1781636 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6089. Min Act: -0.0000

Data Index: 746136 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5891. Min Act: -0.0000

Data Index: 443129 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1717527 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5694. Min Act: -0.0000

Data Index: 314426 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6217. Min Act: -0.0000

Data Index: 915521 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5458. Min Act: -0.0000

Data Index: 559406 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5816. Min Act: -0.0000

Data Index: 517339 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1552085 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1227236 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5571. Min Act: -0.0000

Data Index: 271951 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1826780 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5341. Min Act: -0.0000

Data Index: 94244 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5631. Min Act: -0.0000

Data Index: 133199 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1121389 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5156. Min Act: -0.0000

Data Index: 928121 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1105269 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 0.8213. Min Range: -0.8213

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1356106 (The Pile)

Max Activating Token Index: 331