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

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

Neuron 1518 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.7268. Min Act: -0.0001

Data Index: 878762 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6972. Min Act: -0.0001

Data Index: 262606 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6608. Min Act: -0.0001

Data Index: 966329 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6694. Min Act: -0.0001

Data Index: 702439 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5930. Min Act: -0.0001

Data Index: 392780 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5785. Min Act: -0.0001

Data Index: 934845 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6011. Min Act: -0.0001

Data Index: 687846 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5638. Min Act: -0.0001

Data Index: 384251 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.8352. Min Act: -0.0001

Data Index: 747653 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6182. Min Act: -0.0001

Data Index: 526593 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5987. Min Act: -0.0001

Data Index: 1029001 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5944. Min Act: -0.0001

Data Index: 163018 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.6058. Min Act: -0.0001

Data Index: 456450 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5884. Min Act: -0.0001

Data Index: 963756 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5589. Min Act: -0.0001

Data Index: 650712 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5398. Min Act: -0.0001

Data Index: 547618 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5806. Min Act: -0.0001

Data Index: 46136 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5397. Min Act: -0.0001

Data Index: 465178 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5783. Min Act: -0.0001

Data Index: 1350577 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.8352. Min Range: -0.8352

Max Act: 0.5657. Min Act: -0.0001

Data Index: 548457 (C4 (Web Text))

Max Activating Token Index: 90