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

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

Neuron 4052 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.9274. Min Act: -0.0001

Data Index: 608744 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8592. Min Act: -0.0001

Data Index: 1203693 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1029424 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8770. Min Act: -0.0001

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8043. Min Act: -0.0001

Data Index: 40754 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7964. Min Act: -0.0001

Data Index: 1128416 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7695. Min Act: -0.0001

Data Index: 507695 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7610. Min Act: -0.0001

Data Index: 54090 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7832. Min Act: -0.0001

Data Index: 788894 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8051. Min Act: -0.0001

Data Index: 1351858 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1345280 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7676. Min Act: -0.0001

Data Index: 206402 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7880. Min Act: -0.0001

Data Index: 116318 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7431. Min Act: -0.0001

Data Index: 423818 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7296. Min Act: -0.0001

Data Index: 855092 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1046508 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7201. Min Act: -0.0001

Data Index: 1084816 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7389. Min Act: -0.0001

Data Index: 1204805 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7357. Min Act: -0.0001

Data Index: 671945 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7557. Min Act: -0.0001

Data Index: 954671 (C4 (Web Text))

Max Activating Token Index: 153