Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 343 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0005

Data Index: 651892 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1200. Min Act: -0.0005

Data Index: 614780 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1150. Min Act: -0.0005

Data Index: 1072086 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1145. Min Act: -0.0005

Data Index: 575487 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1146. Min Act: -0.0005

Data Index: 770835 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1144. Min Act: -0.0005

Data Index: 1028767 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1174. Min Act: -0.0005

Data Index: 470835 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1131. Min Act: -0.0005

Data Index: 262038 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1133. Min Act: -0.0005

Data Index: 924240 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1107. Min Act: -0.0005

Data Index: 228711 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1073. Min Act: -0.0005

Data Index: 17611 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1072. Min Act: -0.0005

Data Index: 1318130 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1031. Min Act: -0.0005

Data Index: 173132 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1059. Min Act: -0.0005

Data Index: 966712 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1084. Min Act: -0.0005

Data Index: 1351275 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1052. Min Act: -0.0005

Data Index: 1098463 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1078. Min Act: -0.0005

Data Index: 361403 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1054. Min Act: -0.0005

Data Index: 475420 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1059. Min Act: -0.0005

Data Index: 1156344 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1053. Min Act: -0.0005

Data Index: 88477 (C4 (Web Text))

Max Activating Token Index: 524