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

Dataset: The Pile

Neuron 3106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1651937 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1998220 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1525558 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4337. Min Act: -0.0000

Data Index: 310603 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1205107 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1971200 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1567143 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1485387 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2371. Min Act: -0.0000

Data Index: 1694457 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1989. Min Act: -0.0000

Data Index: 384242 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1864602 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2268. Min Act: -0.0000

Data Index: 1335964 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1874. Min Act: -0.0000

Data Index: 265112 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1235846 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2638. Min Act: -0.0000

Data Index: 1001273 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1931625 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1045904 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1278849 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1808. Min Act: -0.0000

Data Index: 178744 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1262. Min Act: -0.0000

Data Index: 812202 (The Pile)

Max Activating Token Index: 718