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

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

Neuron 2772 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: 3.0602. Min Range: -3.0602

Max Act: 3.0602. Min Act: -0.0002

Data Index: 1154947 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.0602. Min Range: -3.0602

Max Act: 3.0120. Min Act: -0.0002

Data Index: 750471 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.9747. Min Act: -0.0001

Data Index: 502755 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.5905. Min Act: -0.0002

Data Index: 652551 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.7324. Min Act: -0.0002

Data Index: 518490 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 3.0602. Min Range: -3.0602

Max Act: 3.0417. Min Act: -0.0001

Data Index: 320064 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.6146. Min Act: -0.0002

Data Index: 164941 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.6383. Min Act: -0.0001

Data Index: 200184 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.5137. Min Act: -0.0002

Data Index: 1330235 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.8345. Min Act: -0.0002

Data Index: 949249 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.5883. Min Act: -0.0002

Data Index: 14712 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.3024. Min Act: -0.0001

Data Index: 846552 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.5715. Min Act: -0.0002

Data Index: 251906 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.2949. Min Act: -0.0001

Data Index: 688750 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.4819. Min Act: -0.0002

Data Index: 1249486 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.4291. Min Act: -0.0002

Data Index: 91098 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.5224. Min Act: -0.0001

Data Index: 84402 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.4893. Min Act: -0.0002

Data Index: 81542 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.4402. Min Act: -0.0002

Data Index: 333814 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 3.0602. Min Range: -3.0602

Max Act: 2.1336. Min Act: -0.0002

Data Index: 172530 (C4 (Web Text))

Max Activating Token Index: 494