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

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

Neuron 3142 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0334. Min Range: -1.0334

Max Act: 1.0334. Min Act: -0.0001

Data Index: 427439 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9549. Min Act: -0.0001

Data Index: 87979 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9736. Min Act: -0.0001

Data Index: 1212733 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9946. Min Act: -0.0001

Data Index: 353002 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9287. Min Act: -0.0001

Data Index: 790213 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8643. Min Act: -0.0001

Data Index: 914677 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9108. Min Act: -0.0001

Data Index: 762895 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8879. Min Act: -0.0001

Data Index: 523482 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8782. Min Act: -0.0001

Data Index: 587390 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8944. Min Act: -0.0001

Data Index: 701324 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8938. Min Act: -0.0001

Data Index: 1344726 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1295944 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8987. Min Act: -0.0001

Data Index: 261696 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8690. Min Act: -0.0001

Data Index: 242022 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8192. Min Act: -0.0001

Data Index: 157905 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8330. Min Act: -0.0001

Data Index: 273004 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8597. Min Act: -0.0001

Data Index: 1047466 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8701. Min Act: -0.0001

Data Index: 604177 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8635. Min Act: -0.0001

Data Index: 461106 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8131. Min Act: -0.0001

Data Index: 770555 (C4 (Web Text))

Max Activating Token Index: 538