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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2743 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.5812. Min Act: -0.0001

Data Index: 1212902 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.7197. Min Act: -0.0001

Data Index: 730875 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.1307. Min Act: -0.0001

Data Index: 533597 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.2582. Min Act: -0.0001

Data Index: 456202 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.1623. Min Act: -0.0001

Data Index: 812353 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.1277. Min Act: -0.0001

Data Index: 68618 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0681. Min Act: -0.0001

Data Index: 37040 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.2050. Min Act: -0.0001

Data Index: 247913 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.3227. Min Act: -0.0001

Data Index: 724281 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0340. Min Act: -0.0001

Data Index: 148709 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0164. Min Act: -0.0001

Data Index: 78502 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.0128. Min Act: -0.0001

Data Index: 419146 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.7197. Min Range: -3.7197

Max Act: 3.1210. Min Act: -0.0001

Data Index: 562222 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.9325. Min Act: -0.0001

Data Index: 1145670 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.7851. Min Act: -0.0001

Data Index: 194119 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.8951. Min Act: -0.0001

Data Index: 944269 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.7629. Min Act: -0.0001

Data Index: 1039368 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.8796. Min Act: -0.0001

Data Index: 495095 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.7211. Min Act: -0.0001

Data Index: 786198 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 3.7197. Min Range: -3.7197

Max Act: 2.6981. Min Act: -0.0001

Data Index: 1065064 (C4 (Web Text))

Max Activating Token Index: 231