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

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

Neuron 551 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2935. Min Act: -0.0002

Data Index: 693103 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.2093. Min Act: -0.0002

Data Index: 339370 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1443. Min Act: -0.0002

Data Index: 675988 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1387. Min Act: -0.0002

Data Index: 425627 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1424. Min Act: -0.0002

Data Index: 834949 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1313. Min Act: -0.0002

Data Index: 650257 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1446. Min Act: -0.0002

Data Index: 619891 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1392. Min Act: -0.0002

Data Index: 600705 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1467. Min Act: -0.0002

Data Index: 210921 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1275. Min Act: -0.0002

Data Index: 1072241 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1393. Min Act: -0.0002

Data Index: 215717 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1148. Min Act: -0.0002

Data Index: 2111 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1176. Min Act: -0.0002

Data Index: 299503 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1266. Min Act: -0.0002

Data Index: 182733 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1292. Min Act: -0.0002

Data Index: 231621 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1138. Min Act: -0.0002

Data Index: 387757 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1199. Min Act: -0.0002

Data Index: 865942 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1198. Min Act: -0.0002

Data Index: 685334 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1153. Min Act: -0.0002

Data Index: 475444 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.2935. Min Range: -0.2935

Max Act: 0.1153. Min Act: -0.0002

Data Index: 672278 (C4 (Web Text))

Max Activating Token Index: 344