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

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

Neuron 4856 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.1489. Min Act: -0.0002

Data Index: 296850 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.1391. Min Act: -0.0002

Data Index: 833755 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.1129. Min Act: -0.0003

Data Index: 896083 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0982. Min Act: -0.0002

Data Index: 810755 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0975. Min Act: -0.0002

Data Index: 314711 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0887. Min Act: -0.0002

Data Index: 3539 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0960. Min Act: -0.0002

Data Index: 462457 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0792. Min Act: -0.0002

Data Index: 327779 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0823. Min Act: -0.0002

Data Index: 947590 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0859. Min Act: -0.0002

Data Index: 332540 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0693. Min Act: -0.0002

Data Index: 450637 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0822. Min Act: -0.0002

Data Index: 117972 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0667. Min Act: -0.0003

Data Index: 587884 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0813. Min Act: -0.0002

Data Index: 343840 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0665. Min Act: -0.0002

Data Index: 1213945 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0927. Min Act: -0.0002

Data Index: 518342 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0760. Min Act: -0.0002

Data Index: 121847 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0683. Min Act: -0.0002

Data Index: 601875 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0510. Min Act: -0.0002

Data Index: 1199148 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.1489. Min Range: -1.1489

Max Act: 1.0696. Min Act: -0.0002

Data Index: 927766 (C4 (Web Text))

Max Activating Token Index: 75