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

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

Neuron 5093 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9620. Min Act: -0.0000

Data Index: 384594 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1216447 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9880. Min Act: -0.0000

Data Index: 762092 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8491. Min Act: -0.0000

Data Index: 227808 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8876. Min Act: -0.0000

Data Index: 266282 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1251924 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8380. Min Act: -0.0000

Data Index: 5635 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8565. Min Act: -0.0000

Data Index: 508296 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8844. Min Act: -0.0000

Data Index: 406228 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8507. Min Act: -0.0000

Data Index: 132565 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8477. Min Act: -0.0000

Data Index: 311337 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1285858 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1019796 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8392. Min Act: -0.0000

Data Index: 758462 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8297. Min Act: -0.0000

Data Index: 876663 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1218910 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7791. Min Act: -0.0000

Data Index: 33130 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1126167 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7942. Min Act: -0.0000

Data Index: 443279 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7591. Min Act: -0.0000

Data Index: 540766 (C4 (Web Text))

Max Activating Token Index: 859