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

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

Neuron 4422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.9197. Min Act: -0.0000

Data Index: 907642 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.8108. Min Act: -0.0000

Data Index: 239914 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1210146 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1297082 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1211917 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7749. Min Act: -0.0000

Data Index: 145524 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7520. Min Act: -0.0000

Data Index: 767622 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1012072 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7440. Min Act: -0.0000

Data Index: 945897 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1327670 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6918. Min Act: -0.0000

Data Index: 821579 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7098. Min Act: -0.0000

Data Index: 644191 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1183950 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7117. Min Act: -0.0000

Data Index: 756862 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1206052 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1137328 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6982. Min Act: -0.0000

Data Index: 537428 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6950. Min Act: -0.0000

Data Index: 70047 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.6836. Min Act: -0.0000

Data Index: 144000 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.9197. Min Range: -0.9197

Max Act: 0.7044. Min Act: -0.0000

Data Index: 939587 (C4 (Web Text))

Max Activating Token Index: 769