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

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

Neuron 1327 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.0001

Data Index: 494822 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8114. Min Act: -0.0001

Data Index: 260089 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7957. Min Act: -0.0001

Data Index: 807285 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1134099 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6748. Min Act: -0.0001

Data Index: 1534572 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7147. Min Act: -0.0001

Data Index: 1434894 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6794. Min Act: -0.0001

Data Index: 1528789 (Python Code)

Max Activating Token Index: 148

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6584. Min Act: -0.0001

Data Index: 802479 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7122. Min Act: -0.0001

Data Index: 59825 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1564146 (Python Code)

Max Activating Token Index: 765

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5743. Min Act: -0.0001

Data Index: 1643377 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7658. Min Act: -0.0001

Data Index: 298776 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7208. Min Act: -0.0001

Data Index: 760408 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7208. Min Act: -0.0001

Data Index: 971744 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6941. Min Act: -0.0001

Data Index: 1469446 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7368. Min Act: -0.0001

Data Index: 1085001 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7376. Min Act: -0.0001

Data Index: 1079197 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7381. Min Act: -0.0001

Data Index: 852301 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6937. Min Act: -0.0001

Data Index: 4958 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7182. Min Act: -0.0001

Data Index: 898395 (C4 (Web Text))

Max Activating Token Index: 111