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

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

Neuron 2554 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.4435. Min Act: -0.0001

Data Index: 126545 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.3457. Min Act: -0.0001

Data Index: 83127 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1599. Min Act: -0.0001

Data Index: 1187718 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.3589. Min Act: -0.0001

Data Index: 1047578 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2419. Min Act: -0.0001

Data Index: 1198577 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2766. Min Act: -0.0001

Data Index: 136013 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2279. Min Act: -0.0001

Data Index: 655185 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2075. Min Act: -0.0001

Data Index: 1067381 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1512. Min Act: -0.0001

Data Index: 872868 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.3394. Min Act: -0.0001

Data Index: 1173262 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.2627. Min Act: -0.0001

Data Index: 699112 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0873. Min Act: -0.0001

Data Index: 1052930 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0466. Min Act: -0.0001

Data Index: 644050 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1049. Min Act: -0.0001

Data Index: 400161 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0315. Min Act: -0.0001

Data Index: 743190 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1101. Min Act: -0.0001

Data Index: 900602 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0540. Min Act: -0.0001

Data Index: 795995 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1114796 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.1188. Min Act: -0.0001

Data Index: 469331 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 1.4435. Min Range: -1.4435

Max Act: 1.0471. Min Act: -0.0001

Data Index: 354387 (C4 (Web Text))

Max Activating Token Index: 508