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

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

Neuron 1581 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.8393. Min Act: -0.0001

Data Index: 256383 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.5224. Min Act: -0.0001

Data Index: 103358 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3372. Min Act: -0.0001

Data Index: 538680 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.4234. Min Act: -0.0002

Data Index: 1339488 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3506. Min Act: -0.0002

Data Index: 408126 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3793. Min Act: -0.0001

Data Index: 461535 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3836. Min Act: -0.0002

Data Index: 1239969 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3238. Min Act: -0.0002

Data Index: 1331096 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3834. Min Act: -0.0002

Data Index: 645352 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3134. Min Act: -0.0002

Data Index: 902778 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.0875. Min Act: -0.0002

Data Index: 299025 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.0766. Min Act: -0.0002

Data Index: 317375 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.2055. Min Act: -0.0002

Data Index: 678159 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.2652. Min Act: -0.0001

Data Index: 76396 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.0985. Min Act: -0.0002

Data Index: 419327 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.3304. Min Act: -0.0001

Data Index: 102499 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.1407. Min Act: -0.0002

Data Index: 1326655 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.1094. Min Act: -0.0002

Data Index: 545630 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.1158. Min Act: -0.0002

Data Index: 846512 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.8393. Min Range: -1.8393

Max Act: 1.1405. Min Act: -0.0001

Data Index: 187951 (C4 (Web Text))

Max Activating Token Index: 321