Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4295 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.7438. Min Act: -0.0000

Data Index: 53090 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.7099. Min Act: -0.0000

Data Index: 143691 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6919. Min Act: -0.0000

Data Index: 424352 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1308373 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6497. Min Act: -0.0000

Data Index: 932966 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6537. Min Act: -0.0000

Data Index: 155025 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6424. Min Act: -0.0000

Data Index: 885257 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6371. Min Act: -0.0000

Data Index: 628163 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6124. Min Act: -0.0000

Data Index: 104520 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6305. Min Act: -0.0000

Data Index: 815533 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6371. Min Act: -0.0000

Data Index: 779346 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1117020 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.6100. Min Act: -0.0000

Data Index: 215660 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5857. Min Act: -0.0000

Data Index: 643269 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5768. Min Act: -0.0000

Data Index: 1196912 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5685. Min Act: -0.0000

Data Index: 292359 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5921. Min Act: -0.0000

Data Index: 499043 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5930. Min Act: -0.0000

Data Index: 89842 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1081481 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.7438. Min Range: -0.7438

Max Act: 0.5700. Min Act: -0.0000

Data Index: 382462 (C4 (Web Text))

Max Activating Token Index: 678