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

Dataset: The Pile

Neuron 2518 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: 1.1348. Min Range: -1.1348

Max Act: 1.1348. Min Act: -0.0000

Data Index: 471497 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1264845 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1612092 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1964727 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0143. Min Act: -0.0000

Data Index: 104313 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0003. Min Act: -0.0000

Data Index: 222607 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9874. Min Act: -0.0000

Data Index: 863249 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0210. Min Act: -0.0000

Data Index: 613466 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0436. Min Act: -0.0000

Data Index: 187671 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1865806 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9852. Min Act: -0.0000

Data Index: 859560 (The Pile)

Max Activating Token Index: 216

Text #11

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1219960 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1757829 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1564290 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9465. Min Act: -0.0000

Data Index: 362630 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9692. Min Act: -0.0000

Data Index: 488575 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9667. Min Act: -0.0000

Data Index: 345021 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 1.1348. Min Range: -1.1348

Max Act: 1.0201. Min Act: -0.0000

Data Index: 267050 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.8983. Min Act: -0.0000

Data Index: 54097 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 1.1348. Min Range: -1.1348

Max Act: 0.9613. Min Act: -0.0000

Data Index: 417136 (The Pile)

Max Activating Token Index: 716