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

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

Neuron 2028 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3943. Min Act: -0.0003

Data Index: 1008985 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3641. Min Act: -0.0003

Data Index: 1222284 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3579. Min Act: -0.0003

Data Index: 981176 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3512. Min Act: -0.0003

Data Index: 560769 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3435. Min Act: -0.0003

Data Index: 1050632 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3378. Min Act: -0.0003

Data Index: 30458 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3242. Min Act: -0.0003

Data Index: 730220 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3190. Min Act: -0.0003

Data Index: 461842 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3297. Min Act: -0.0003

Data Index: 644759 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3177. Min Act: -0.0003

Data Index: 170133 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3133. Min Act: -0.0003

Data Index: 188535 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3126. Min Act: -0.0002

Data Index: 663686 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3117. Min Act: -0.0002

Data Index: 77727 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3118. Min Act: -0.0003

Data Index: 26289 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3071. Min Act: -0.0003

Data Index: 664581 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3069. Min Act: -0.0003

Data Index: 38184 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3060. Min Act: -0.0003

Data Index: 641329 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.3016. Min Act: -0.0003

Data Index: 874387 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2943. Min Act: -0.0003

Data Index: 624832 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.3943. Min Range: -0.3943

Max Act: 0.2929. Min Act: -0.0003

Data Index: 915530 (C4 (Web Text))

Max Activating Token Index: 306