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

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

Neuron 3295 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2506. Min Act: -0.0001

Data Index: 588223 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2560. Min Act: -0.0001

Data Index: 385840 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2291. Min Act: -0.0002

Data Index: 903783 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2266. Min Act: -0.0002

Data Index: 140127 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2261. Min Act: -0.0001

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2082. Min Act: -0.0002

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2060. Min Act: -0.0002

Data Index: 249877 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2215. Min Act: -0.0002

Data Index: 361217 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2064. Min Act: -0.0001

Data Index: 152643 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2142. Min Act: -0.0002

Data Index: 216835 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2118. Min Act: -0.0001

Data Index: 674905 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2128. Min Act: -0.0002

Data Index: 369416 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2072. Min Act: -0.0001

Data Index: 409938 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2088. Min Act: -0.0002

Data Index: 623476 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2214. Min Act: -0.0002

Data Index: 345322 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2072. Min Act: -0.0002

Data Index: 1188681 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1348762 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.1978. Min Act: -0.0001

Data Index: 242116 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2047. Min Act: -0.0002

Data Index: 967536 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.2560. Min Range: -0.2560

Max Act: 0.2107. Min Act: -0.0002

Data Index: 1242470 (C4 (Web Text))

Max Activating Token Index: 94