Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 137 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2840. Min Act: -0.0001

Data Index: 480857 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2643. Min Act: -0.0001

Data Index: 901008 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2445. Min Act: -0.0000

Data Index: 963555 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2360. Min Act: -0.0001

Data Index: 401768 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2569. Min Act: -0.0001

Data Index: 352855 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2414. Min Act: -0.0001

Data Index: 314393 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2449. Min Act: -0.0000

Data Index: 60092 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2418. Min Act: -0.0001

Data Index: 558053 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2225. Min Act: -0.0001

Data Index: 19938 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2275. Min Act: -0.0001

Data Index: 822040 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2280. Min Act: -0.0001

Data Index: 368288 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1336550 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2275. Min Act: -0.0001

Data Index: 82836 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1059778 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2126. Min Act: -0.0001

Data Index: 224164 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2219. Min Act: -0.0001

Data Index: 696308 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2190. Min Act: -0.0001

Data Index: 870096 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2246. Min Act: -0.0001

Data Index: 82814 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2046. Min Act: -0.0001

Data Index: 114515 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.2840. Min Range: -0.2840

Max Act: 0.2163. Min Act: -0.0001

Data Index: 713200 (C4 (Web Text))

Max Activating Token Index: 947