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

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

Neuron 3798 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2273. Min Range: -1.2273

Max Act: 1.1113. Min Act: -0.0000

Data Index: 41488 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.2273. Min Range: -1.2273

Max Act: 1.2273. Min Act: -0.0000

Data Index: 626758 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1192460 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 1.2273. Min Range: -1.2273

Max Act: 1.0136. Min Act: -0.0000

Data Index: 151248 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 1.2273. Min Range: -1.2273

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1327624 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1059853 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.9233. Min Act: -0.0000

Data Index: 962886 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.9176. Min Act: 0.0000

Data Index: 150055 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.9116. Min Act: -0.0000

Data Index: 393942 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1292747 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8624. Min Act: -0.0000

Data Index: 727058 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8063. Min Act: 0.0000

Data Index: 550077 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8010. Min Act: -0.0000

Data Index: 316436 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1088023 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8732. Min Act: -0.0000

Data Index: 410395 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8126. Min Act: -0.0000

Data Index: 399577 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1013363 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1187735 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.8362. Min Act: 0.0001

Data Index: 645894 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 1.2273. Min Range: -1.2273

Max Act: 0.7844. Min Act: -0.0000

Data Index: 668870 (C4 (Web Text))

Max Activating Token Index: 85