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

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

Neuron 1897 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: 0.4233. Min Range: -0.4233

Max Act: 0.4176. Min Act: -0.0001

Data Index: 478015 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4233. Min Act: -0.0001

Data Index: 762570 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1088852 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.4127. Min Act: -0.0001

Data Index: 577220 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3432. Min Act: -0.0001

Data Index: 667161 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3571. Min Act: -0.0001

Data Index: 1297238 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3705. Min Act: -0.0001

Data Index: 647351 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3703. Min Act: -0.0001

Data Index: 187125 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3772. Min Act: -0.0001

Data Index: 182718 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3732. Min Act: -0.0001

Data Index: 83515 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3524. Min Act: -0.0001

Data Index: 797082 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3766. Min Act: -0.0001

Data Index: 1188504 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3488. Min Act: -0.0001

Data Index: 914279 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3615. Min Act: -0.0001

Data Index: 330779 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3639. Min Act: -0.0001

Data Index: 84761 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3666. Min Act: -0.0001

Data Index: 1322641 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3338. Min Act: -0.0001

Data Index: 140696 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3293. Min Act: -0.0001

Data Index: 326062 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3357. Min Act: -0.0001

Data Index: 1022633 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.4233. Min Range: -0.4233

Max Act: 0.3104. Min Act: -0.0001

Data Index: 783858 (C4 (Web Text))

Max Activating Token Index: 694