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

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

Neuron 306 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5517. Min Act: -0.0000

Data Index: 627174 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5538. Min Act: -0.0001

Data Index: 677241 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1096364 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5030. Min Act: -0.0001

Data Index: 153449 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4386. Min Act: -0.0000

Data Index: 18646 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4158. Min Act: -0.0001

Data Index: 950030 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1167950 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4394. Min Act: -0.0000

Data Index: 377412 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4194. Min Act: -0.0000

Data Index: 519003 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4062. Min Act: -0.0000

Data Index: 831761 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4022. Min Act: -0.0001

Data Index: 508303 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4019. Min Act: -0.0000

Data Index: 497267 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4306. Min Act: -0.0001

Data Index: 624852 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4107. Min Act: -0.0000

Data Index: 137738 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4089. Min Act: -0.0001

Data Index: 690269 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4090. Min Act: -0.0000

Data Index: 158620 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3825. Min Act: -0.0000

Data Index: 469125 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3712. Min Act: -0.0000

Data Index: 114697 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3744. Min Act: -0.0000

Data Index: 738158 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.3919. Min Act: -0.0001

Data Index: 926235 (C4 (Web Text))

Max Activating Token Index: 908