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

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

Neuron 3088 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1133. Min Range: -1.1133

Max Act: 1.1133. Min Act: -0.0000

Data Index: 522273 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 1.1133. Min Range: -1.1133

Max Act: 1.0584. Min Act: -0.0000

Data Index: 160335 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9877. Min Act: -0.0001

Data Index: 518471 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9130. Min Act: -0.0001

Data Index: 1649419 (Python Code)

Max Activating Token Index: 606

Text #4

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1552014 (Python Code)

Max Activating Token Index: 917

Text #5

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8751. Min Act: -0.0000

Data Index: 143797 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8206. Min Act: -0.0000

Data Index: 432387 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.9055. Min Act: -0.0000

Data Index: 574743 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8705. Min Act: -0.0000

Data Index: 274277 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1073823 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8334. Min Act: -0.0001

Data Index: 1589651 (Python Code)

Max Activating Token Index: 865

Text #11

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8908. Min Act: -0.0000

Data Index: 908499 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1633186 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1093261 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.8459. Min Act: -0.0001

Data Index: 1644085 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7099. Min Act: -0.0000

Data Index: 678212 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1438473 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1254243 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1538063 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 1.1133. Min Range: -1.1133

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1455724 (Python Code)

Max Activating Token Index: 427