Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3840 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4520. Min Act: -0.0000

Data Index: 700455 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3720. Min Act: -0.0000

Data Index: 475646 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4010. Min Act: -0.0000

Data Index: 288555 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4225. Min Act: -0.0000

Data Index: 11469 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4283. Min Act: -0.0000

Data Index: 169011 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4086. Min Act: -0.0000

Data Index: 806981 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1124210 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.4082. Min Act: -0.0000

Data Index: 938021 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3268. Min Act: -0.0000

Data Index: 657087 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1038719 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3514. Min Act: -0.0000

Data Index: 520727 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3075. Min Act: -0.0000

Data Index: 849408 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3213. Min Act: -0.0000

Data Index: 84318 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3160. Min Act: -0.0000

Data Index: 406650 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3225. Min Act: -0.0000

Data Index: 788913 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3105. Min Act: -0.0000

Data Index: 269018 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.2925. Min Act: -0.0000

Data Index: 596703 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3271. Min Act: -0.0000

Data Index: 670270 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3141. Min Act: -0.0000

Data Index: 905862 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.4520. Min Range: -0.4520

Max Act: 0.3005. Min Act: -0.0000

Data Index: 688810 (C4 (Web Text))

Max Activating Token Index: 891