Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2343 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.6395. Min Act: -0.0001

Data Index: 713880 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.6123. Min Act: -0.0001

Data Index: 23214 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.6354. Min Act: -0.0001

Data Index: 323040 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5885. Min Act: -0.0001

Data Index: 162849 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5905. Min Act: -0.0001

Data Index: 39924 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5834. Min Act: -0.0001

Data Index: 645829 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5676. Min Act: -0.0001

Data Index: 463205 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5887. Min Act: -0.0001

Data Index: 361210 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5594. Min Act: -0.0002

Data Index: 709945 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5932. Min Act: -0.0002

Data Index: 1141123 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5175. Min Act: -0.0002

Data Index: 526661 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5832. Min Act: -0.0001

Data Index: 387150 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.6055. Min Act: -0.0001

Data Index: 613565 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5859. Min Act: -0.0001

Data Index: 810949 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5760. Min Act: -0.0001

Data Index: 955176 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5777. Min Act: -0.0001

Data Index: 441982 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5683. Min Act: -0.0002

Data Index: 1098770 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5704. Min Act: -0.0002

Data Index: 382047 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.6042. Min Act: -0.0001

Data Index: 868379 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.6395. Min Range: -0.6395

Max Act: 0.5871. Min Act: -0.0001

Data Index: 232873 (C4 (Web Text))

Max Activating Token Index: 174