Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 555 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.0235. Min Act: -0.0001

Data Index: 1143258 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.0690. Min Act: -0.0001

Data Index: 990266 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.1477. Min Act: -0.0001

Data Index: 211690 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.0218. Min Act: -0.0001

Data Index: 706042 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9809. Min Act: -0.0001

Data Index: 1227454 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.0445. Min Act: -0.0001

Data Index: 429817 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.0309. Min Act: -0.0001

Data Index: 824700 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1098330 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9038. Min Act: -0.0001

Data Index: 688551 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9938. Min Act: -0.0001

Data Index: 334235 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9049. Min Act: -0.0001

Data Index: 1333163 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.0117. Min Act: -0.0001

Data Index: 1022816 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9204. Min Act: -0.0001

Data Index: 13501 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.8608. Min Act: -0.0001

Data Index: 743162 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9034. Min Act: -0.0001

Data Index: 375272 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.8737. Min Act: -0.0001

Data Index: 1182301 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9324. Min Act: -0.0001

Data Index: 1076553 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.1477. Min Range: -1.1477

Max Act: 1.0157. Min Act: -0.0001

Data Index: 449638 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9878. Min Act: -0.0001

Data Index: 1022115 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 1.1477. Min Range: -1.1477

Max Act: 0.9299. Min Act: -0.0001

Data Index: 263936 (C4 (Web Text))

Max Activating Token Index: 14