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

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

Neuron 4159 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.6285. Min Act: -0.0003

Data Index: 45623 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.5801. Min Act: -0.0002

Data Index: 197648 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.5440. Min Act: -0.0003

Data Index: 261767 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.5616. Min Act: -0.0002

Data Index: 77423 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.5439. Min Act: -0.0002

Data Index: 840882 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4849. Min Act: -0.0002

Data Index: 1095551 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4152. Min Act: -0.0002

Data Index: 958344 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4470. Min Act: -0.0002

Data Index: 452793 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4469. Min Act: -0.0002

Data Index: 453460 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4423. Min Act: -0.0003

Data Index: 840988 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4461. Min Act: -0.0002

Data Index: 1284187 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4086. Min Act: -0.0002

Data Index: 661673 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.3989. Min Act: -0.0002

Data Index: 782335 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.4132. Min Act: -0.0003

Data Index: 421146 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.3857. Min Act: -0.0002

Data Index: 1219732 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.3687. Min Act: -0.0003

Data Index: 654852 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.3779. Min Act: -0.0002

Data Index: 450302 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.3865. Min Act: -0.0002

Data Index: 1134075 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.3506. Min Act: -0.0002

Data Index: 347885 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 1.6285. Min Range: -1.6285

Max Act: 1.3615. Min Act: -0.0002

Data Index: 81330 (C4 (Web Text))

Max Activating Token Index: 12