Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1868 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7685. Min Act: -0.0001

Data Index: 412891 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7651. Min Act: -0.0001

Data Index: 73477 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1152348 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7942. Min Act: -0.0001

Data Index: 1297916 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7700. Min Act: -0.0001

Data Index: 662085 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7328. Min Act: -0.0001

Data Index: 218072 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7612. Min Act: -0.0001

Data Index: 954752 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7099. Min Act: -0.0001

Data Index: 232309 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6535. Min Act: -0.0001

Data Index: 1243554 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7465. Min Act: -0.0001

Data Index: 1140336 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6752. Min Act: -0.0001

Data Index: 776369 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7219. Min Act: -0.0001

Data Index: 1133379 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1149130 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7205. Min Act: -0.0001

Data Index: 1254635 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7075. Min Act: -0.0001

Data Index: 936417 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7340. Min Act: -0.0001

Data Index: 1324867 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7290. Min Act: -0.0001

Data Index: 527400 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6985. Min Act: -0.0001

Data Index: 905896 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.7029. Min Act: -0.0001

Data Index: 748898 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.7947. Min Range: -0.7947

Max Act: 0.6988. Min Act: -0.0001

Data Index: 503385 (C4 (Web Text))

Max Activating Token Index: 176