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

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

Neuron 6034 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1027098 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1294825 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.9065. Min Act: 0.0001

Data Index: 828661 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.8879. Min Act: -0.0000

Data Index: 953609 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1032819 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7945. Min Act: -0.0000

Data Index: 62403 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7545. Min Act: -0.0000

Data Index: 157980 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7536. Min Act: -0.0000

Data Index: 65267 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7980. Min Act: 0.0000

Data Index: 1077523 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7730. Min Act: -0.0000

Data Index: 642597 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7547. Min Act: -0.0000

Data Index: 308557 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7407. Min Act: -0.0000

Data Index: 83586 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1142198 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1340197 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7060. Min Act: -0.0000

Data Index: 717603 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7177. Min Act: 0.0000

Data Index: 471754 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6869. Min Act: -0.0000

Data Index: 610370 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6996. Min Act: 0.0000

Data Index: 267447 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.7259. Min Act: 0.0000

Data Index: 637209 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.9232. Min Range: -0.9232

Max Act: 0.6900. Min Act: -0.0000

Data Index: 357355 (C4 (Web Text))

Max Activating Token Index: 378