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

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

Neuron 2079 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: 1.2166. Min Range: -1.2166

Max Act: 1.2166. Min Act: -0.0001

Data Index: 426834 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8610. Min Act: -0.0001

Data Index: 958169 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7900. Min Act: -0.0001

Data Index: 1253485 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8149. Min Act: -0.0001

Data Index: 173035 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7657. Min Act: -0.0001

Data Index: 978699 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7136. Min Act: -0.0001

Data Index: 947638 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1098842 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6744. Min Act: -0.0001

Data Index: 709007 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6665. Min Act: -0.0001

Data Index: 1318169 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7683. Min Act: -0.0001

Data Index: 69450 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1150254 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.5304. Min Act: -0.0001

Data Index: 927973 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6981. Min Act: -0.0001

Data Index: 674408 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6103. Min Act: -0.0002

Data Index: 802736 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1130068 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.5169. Min Act: -0.0001

Data Index: 672353 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.4991. Min Act: -0.0001

Data Index: 523172 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6361. Min Act: -0.0001

Data Index: 649958 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.5485. Min Act: -0.0001

Data Index: 912508 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.6160. Min Act: -0.0001

Data Index: 854139 (C4 (Web Text))

Max Activating Token Index: 27