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

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

Neuron 1536 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.1457. Min Range: -9.1457

Max Act: 9.1457. Min Act: -0.0000

Data Index: 467750 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 9.1457. Min Range: -9.1457

Max Act: 9.1197. Min Act: -0.0000

Data Index: 1173232 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.8370. Min Act: -0.0000

Data Index: 681418 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 9.1457. Min Range: -9.1457

Max Act: 8.7358. Min Act: -0.0000

Data Index: 929679 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.3174. Min Act: -0.0000

Data Index: 355423 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.2492. Min Act: -0.0000

Data Index: 957816 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.6772. Min Act: -0.0000

Data Index: 944313 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.9429. Min Act: -0.0000

Data Index: 1262002 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.0648. Min Act: -0.0000

Data Index: 26246 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.1895. Min Act: -0.0000

Data Index: 1278647 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 9.1457. Min Range: -9.1457

Max Act: 7.1345. Min Act: -0.0000

Data Index: 1236174 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 9.1457. Min Range: -9.1457

Max Act: 6.8829. Min Act: -0.0000

Data Index: 818328 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 9.1457. Min Range: -9.1457

Max Act: 6.8299. Min Act: -0.0000

Data Index: 128234 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 9.1457. Min Range: -9.1457

Max Act: 6.7143. Min Act: -0.0000

Data Index: 317168 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 9.1457. Min Range: -9.1457

Max Act: 6.4817. Min Act: -0.0000

Data Index: 127269 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 9.1457. Min Range: -9.1457

Max Act: 6.1364. Min Act: -0.0000

Data Index: 801434 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 9.1457. Min Range: -9.1457

Max Act: 5.7534. Min Act: -0.0000

Data Index: 909961 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 9.1457. Min Range: -9.1457

Max Act: 6.1267. Min Act: -0.0000

Data Index: 1059274 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 9.1457. Min Range: -9.1457

Max Act: 6.0882. Min Act: -0.0000

Data Index: 652366 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 9.1457. Min Range: -9.1457

Max Act: 5.8409. Min Act: -0.0000

Data Index: 78845 (C4 (Web Text))

Max Activating Token Index: 642