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

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

Neuron 2834 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: 0.8997. Min Range: -0.8997

Max Act: 0.8997. Min Act: -0.0002

Data Index: 155297 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.8089. Min Act: -0.0002

Data Index: 288060 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.7409. Min Act: -0.0001

Data Index: 1233221 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.7277. Min Act: -0.0002

Data Index: 43736 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6789. Min Act: -0.0002

Data Index: 147184 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6751. Min Act: -0.0002

Data Index: 1137051 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6565. Min Act: -0.0001

Data Index: 1161938 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6902. Min Act: -0.0002

Data Index: 1146168 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6618. Min Act: -0.0001

Data Index: 1529389 (Python Code)

Max Activating Token Index: 691

Text #9

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6244. Min Act: -0.0001

Data Index: 540087 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1589902 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6616. Min Act: -0.0001

Data Index: 885668 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6338. Min Act: -0.0002

Data Index: 991450 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6534. Min Act: -0.0002

Data Index: 761118 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6651. Min Act: -0.0002

Data Index: 492353 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6443. Min Act: -0.0001

Data Index: 36260 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6325. Min Act: -0.0002

Data Index: 160719 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6776. Min Act: -0.0002

Data Index: 460492 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6441. Min Act: -0.0002

Data Index: 776150 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.8997. Min Range: -0.8997

Max Act: 0.6387. Min Act: -0.0002

Data Index: 260308 (C4 (Web Text))

Max Activating Token Index: 427