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

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

Neuron 1650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3818. Min Act: -0.0001

Data Index: 745625 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3586. Min Act: -0.0001

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3540. Min Act: -0.0001

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3454. Min Act: -0.0001

Data Index: 771235 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2734. Min Act: -0.0001

Data Index: 103257 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3160. Min Act: -0.0001

Data Index: 1158035 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2995. Min Act: -0.0001

Data Index: 210840 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3117. Min Act: -0.0001

Data Index: 1207084 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3018. Min Act: -0.0001

Data Index: 953140 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2971. Min Act: -0.0001

Data Index: 669921 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2894. Min Act: -0.0001

Data Index: 274722 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2858. Min Act: -0.0001

Data Index: 604513 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3292. Min Act: -0.0001

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2906. Min Act: -0.0001

Data Index: 1294697 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.3186. Min Act: -0.0001

Data Index: 135577 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2727. Min Act: -0.0001

Data Index: 544352 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1107481 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2982. Min Act: -0.0001

Data Index: 65104 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2856. Min Act: -0.0001

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.3818. Min Range: -0.3818

Max Act: 0.2763. Min Act: -0.0001

Data Index: 339877 (C4 (Web Text))

Max Activating Token Index: 765