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

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

Neuron 1071 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: 1.4845. Min Range: -1.4845

Max Act: 1.4845. Min Act: -0.0002

Data Index: 740734 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3768. Min Act: -0.0002

Data Index: 475888 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3878. Min Act: -0.0002

Data Index: 649454 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3494. Min Act: -0.0002

Data Index: 435789 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3328. Min Act: -0.0002

Data Index: 665110 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3390. Min Act: -0.0002

Data Index: 1263171 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3273. Min Act: -0.0002

Data Index: 991041 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3229. Min Act: -0.0002

Data Index: 324571 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3213. Min Act: -0.0002

Data Index: 632086 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2932. Min Act: -0.0002

Data Index: 221427 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.3237. Min Act: -0.0002

Data Index: 1187961 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2824. Min Act: -0.0003

Data Index: 140837 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2628. Min Act: -0.0002

Data Index: 640133 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2713. Min Act: -0.0003

Data Index: 184944 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2332. Min Act: -0.0002

Data Index: 78362 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2722. Min Act: -0.0002

Data Index: 232787 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2782. Min Act: -0.0002

Data Index: 370065 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2758. Min Act: -0.0002

Data Index: 1111787 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2653. Min Act: -0.0002

Data Index: 5956 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.4845. Min Range: -1.4845

Max Act: 1.2720. Min Act: -0.0002

Data Index: 329791 (C4 (Web Text))

Max Activating Token Index: 245