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

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

Neuron 116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.9368. Min Act: -0.0003

Data Index: 1127711 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8854. Min Act: -0.0003

Data Index: 1149805 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8242. Min Act: -0.0003

Data Index: 883102 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8244. Min Act: -0.0003

Data Index: 1343078 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8514. Min Act: -0.0003

Data Index: 176520 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8252. Min Act: -0.0003

Data Index: 429919 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8397. Min Act: -0.0003

Data Index: 1203244 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8347. Min Act: -0.0003

Data Index: 191746 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7792. Min Act: -0.0003

Data Index: 363358 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8114. Min Act: -0.0003

Data Index: 685488 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8413. Min Act: -0.0003

Data Index: 473388 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8005. Min Act: -0.0003

Data Index: 1058678 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8234. Min Act: -0.0003

Data Index: 966094 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7643. Min Act: -0.0003

Data Index: 297914 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7676. Min Act: -0.0003

Data Index: 430766 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8141. Min Act: -0.0003

Data Index: 1202069 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7782. Min Act: -0.0003

Data Index: 341410 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7765. Min Act: -0.0003

Data Index: 738248 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7470. Min Act: -0.0003

Data Index: 106193 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7471. Min Act: -0.0003

Data Index: 596523 (C4 (Web Text))

Max Activating Token Index: 77