Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3043 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.6161. Min Act: -0.0000

Data Index: 905878 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.6113. Min Act: -0.0000

Data Index: 379694 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5726. Min Act: -0.0000

Data Index: 464469 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5368. Min Act: -0.0000

Data Index: 682171 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.5093. Min Act: -0.0000

Data Index: 481058 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4423. Min Act: -0.0000

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.4033. Min Act: -0.0000

Data Index: 368984 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3968. Min Act: -0.0000

Data Index: 216752 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1124197 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3624. Min Act: -0.0000

Data Index: 631669 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3683. Min Act: -0.0000

Data Index: 902480 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3579. Min Act: -0.0000

Data Index: 760002 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1007474 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3315. Min Act: -0.0000

Data Index: 220186 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1275489 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3204. Min Act: -0.0000

Data Index: 674305 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1067304 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3179. Min Act: -0.0000

Data Index: 309468 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3100. Min Act: -0.0000

Data Index: 279847 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.6161. Min Range: -0.6161

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1113207 (C4 (Web Text))

Max Activating Token Index: 215