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

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

Neuron 4809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3297. Min Range: -2.3297

Max Act: 2.3297. Min Act: -0.0000

Data Index: 331946 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.4346. Min Act: -0.0000

Data Index: 711729 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.5775. Min Act: -0.0001

Data Index: 903771 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.5336. Min Act: -0.0000

Data Index: 513211 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.4337. Min Act: -0.0000

Data Index: 998262 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.2877. Min Act: -0.0000

Data Index: 718067 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.4459. Min Act: -0.0001

Data Index: 1089589 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.5975. Min Act: -0.0001

Data Index: 569435 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1264457 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.3065. Min Act: -0.0000

Data Index: 389593 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.2939. Min Act: -0.0000

Data Index: 66894 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.2422. Min Act: -0.0000

Data Index: 532702 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.3269. Min Act: -0.0000

Data Index: 789721 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.3186. Min Act: -0.0000

Data Index: 600054 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.3081. Min Act: -0.0000

Data Index: 261364 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.1490. Min Act: -0.0000

Data Index: 636036 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1177101 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.1992. Min Act: -0.0000

Data Index: 457426 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1043162 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 2.3297. Min Range: -2.3297

Max Act: 1.2870. Min Act: -0.0000

Data Index: 944334 (C4 (Web Text))

Max Activating Token Index: 222