Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 164 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.0567. Min Range: -1.0567

Max Act: 1.0567. Min Act: -0.0002

Data Index: 772567 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.0567. Min Range: -1.0567

Max Act: 1.0345. Min Act: -0.0002

Data Index: 472864 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9635. Min Act: -0.0002

Data Index: 1027683 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9474. Min Act: -0.0002

Data Index: 218644 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9513. Min Act: -0.0002

Data Index: 1199882 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9673. Min Act: -0.0002

Data Index: 1291234 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9731. Min Act: -0.0002

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9607. Min Act: -0.0002

Data Index: 46765 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9348. Min Act: -0.0002

Data Index: 984134 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9474. Min Act: -0.0002

Data Index: 144192 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9217. Min Act: -0.0002

Data Index: 621808 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9319. Min Act: -0.0002

Data Index: 439019 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9241. Min Act: -0.0002

Data Index: 326387 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9405. Min Act: -0.0002

Data Index: 736512 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9251. Min Act: -0.0002

Data Index: 312502 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9042. Min Act: -0.0002

Data Index: 707329 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9033. Min Act: -0.0002

Data Index: 495842 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8919. Min Act: -0.0002

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9181. Min Act: -0.0002

Data Index: 427319 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9009. Min Act: -0.0002

Data Index: 257852 (C4 (Web Text))

Max Activating Token Index: 260