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

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

Neuron 78 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1339. Min Range: -1.1339

Max Act: 1.1339. Min Act: -0.0001

Data Index: 228290 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 1.1339. Min Range: -1.1339

Max Act: 1.0851. Min Act: -0.0001

Data Index: 1292792 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.9848. Min Act: -0.0001

Data Index: 398580 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.9660. Min Act: -0.0001

Data Index: 1152833 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.9640. Min Act: -0.0001

Data Index: 300960 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.1339. Min Range: -1.1339

Max Act: 1.0474. Min Act: -0.0001

Data Index: 970269 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.9828. Min Act: -0.0001

Data Index: 705963 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.9311. Min Act: -0.0001

Data Index: 383787 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8998. Min Act: -0.0001

Data Index: 810877 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8884. Min Act: -0.0001

Data Index: 321650 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8205. Min Act: -0.0001

Data Index: 876741 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8049. Min Act: -0.0001

Data Index: 308714 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7974. Min Act: -0.0001

Data Index: 84886 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8777. Min Act: -0.0001

Data Index: 288828 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8169. Min Act: -0.0001

Data Index: 502177 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8670. Min Act: -0.0001

Data Index: 61358 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8321. Min Act: -0.0001

Data Index: 981494 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1255199 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.8260. Min Act: -0.0001

Data Index: 131470 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 1.1339. Min Range: -1.1339

Max Act: 0.7836. Min Act: -0.0001

Data Index: 926956 (C4 (Web Text))

Max Activating Token Index: 272