Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3469 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6935. Min Act: -0.0000

Data Index: 502340 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1088555 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5990. Min Act: -0.0000

Data Index: 533130 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1071178 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6355. Min Act: -0.0000

Data Index: 350705 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5656. Min Act: -0.0000

Data Index: 694031 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5041. Min Act: -0.0000

Data Index: 102376 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1333275 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5350. Min Act: -0.0000

Data Index: 622174 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5538. Min Act: -0.0000

Data Index: 234820 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1259305 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5501. Min Act: -0.0000

Data Index: 573025 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5222. Min Act: -0.0000

Data Index: 768390 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5777. Min Act: -0.0000

Data Index: 553600 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5065. Min Act: -0.0000

Data Index: 224833 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1042308 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5333. Min Act: -0.0000

Data Index: 153596 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4975. Min Act: -0.0000

Data Index: 846111 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1093665 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1265052 (C4 (Web Text))

Max Activating Token Index: 171