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

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

Neuron 2636 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: 0.1939. Min Range: -0.1939

Max Act: 0.1939. Min Act: -0.0000

Data Index: 113932 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1529. Min Act: -0.0000

Data Index: 979150 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1618. Min Act: -0.0001

Data Index: 132728 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1193164 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1525. Min Act: -0.0000

Data Index: 684888 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1432. Min Act: -0.0000

Data Index: 665256 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1376. Min Act: -0.0000

Data Index: 438808 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1402. Min Act: -0.0000

Data Index: 868835 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1329. Min Act: -0.0001

Data Index: 494251 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1041204 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1318. Min Act: -0.0001

Data Index: 942153 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1091083 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1407. Min Act: -0.0000

Data Index: 602934 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1248. Min Act: -0.0000

Data Index: 585919 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1379. Min Act: -0.0000

Data Index: 406874 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1284. Min Act: -0.0000

Data Index: 883077 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1318. Min Act: -0.0000

Data Index: 88548 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1209. Min Act: -0.0001

Data Index: 143605 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1302. Min Act: -0.0001

Data Index: 677294 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1329962 (C4 (Web Text))

Max Activating Token Index: 187