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

Dataset: The Pile

Neuron 2638 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: 1.4213. Min Range: -1.4213

Max Act: 1.4213. Min Act: -0.0001

Data Index: 1060159 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.3910. Min Act: -0.0000

Data Index: 640964 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.3467. Min Act: -0.0000

Data Index: 193434 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.4168. Min Act: -0.0000

Data Index: 462046 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1410271 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2487. Min Act: -0.0000

Data Index: 382915 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2769. Min Act: -0.0000

Data Index: 407588 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.3095. Min Act: -0.0000

Data Index: 253825 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1808244 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2825. Min Act: -0.0000

Data Index: 625071 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2127. Min Act: -0.0000

Data Index: 705440 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0448. Min Act: -0.0000

Data Index: 953621 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1439719 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1161066 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1944621 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.2141. Min Act: -0.0001

Data Index: 786030 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1396. Min Act: -0.0000

Data Index: 110255 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1161. Min Act: -0.0000

Data Index: 446498 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1150. Min Act: -0.0000

Data Index: 1300484 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8729. Min Act: -0.0000

Data Index: 114102 (The Pile)

Max Activating Token Index: 720