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

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

Neuron 2103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4289. Min Act: -0.0001

Data Index: 575280 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4108. Min Act: -0.0001

Data Index: 577423 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4164. Min Act: -0.0001

Data Index: 776930 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4182. Min Act: -0.0000

Data Index: 717913 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4134. Min Act: -0.0001

Data Index: 564104 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1075712 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4116. Min Act: -0.0001

Data Index: 468440 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3944. Min Act: -0.0001

Data Index: 1172904 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3921. Min Act: -0.0001

Data Index: 1181121 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4142. Min Act: -0.0001

Data Index: 1200582 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3869. Min Act: -0.0001

Data Index: 825938 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3988. Min Act: -0.0001

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3909. Min Act: -0.0000

Data Index: 561920 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1129023 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3924. Min Act: -0.0001

Data Index: 407253 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3763. Min Act: -0.0001

Data Index: 205432 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3988. Min Act: -0.0001

Data Index: 1018599 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3860. Min Act: -0.0001

Data Index: 736214 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1127197 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.3851. Min Act: -0.0001

Data Index: 1210173 (C4 (Web Text))

Max Activating Token Index: 883