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

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

Neuron 1306 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: 1.3183. Min Range: -1.3183

Max Act: 1.3183. Min Act: -0.0000

Data Index: 724792 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.2678. Min Act: -0.0001

Data Index: 59447 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1999. Min Act: -0.0000

Data Index: 645399 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1103813 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1893. Min Act: -0.0000

Data Index: 151139 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1057. Min Act: -0.0001

Data Index: 1024658 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1185164 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0488. Min Act: -0.0001

Data Index: 948804 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0782. Min Act: -0.0000

Data Index: 701970 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0217. Min Act: -0.0000

Data Index: 594926 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0544. Min Act: -0.0001

Data Index: 306714 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0216. Min Act: -0.0001

Data Index: 517626 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9973. Min Act: -0.0001

Data Index: 182391 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1295696 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9345. Min Act: -0.0000

Data Index: 278282 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9618. Min Act: -0.0000

Data Index: 360020 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9607. Min Act: -0.0001

Data Index: 460808 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9567. Min Act: -0.0001

Data Index: 300351 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9127. Min Act: -0.0000

Data Index: 412376 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9349. Min Act: -0.0000

Data Index: 617614 (C4 (Web Text))

Max Activating Token Index: 415