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

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

Neuron 1262 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.8139. Min Act: -0.0000

Data Index: 806811 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.5849. Min Act: -0.0000

Data Index: 262763 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1375235 (Python Code)

Max Activating Token Index: 348

Text #3

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1445393 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4004. Min Act: -0.0000

Data Index: 860864 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3851. Min Act: -0.0000

Data Index: 781760 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.4204. Min Act: 0.0000

Data Index: 1279287 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3899. Min Act: -0.0000

Data Index: 993449 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3997. Min Act: -0.0000

Data Index: 498378 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3642. Min Act: 0.0000

Data Index: 1177362 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1362674 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3404. Min Act: -0.0000

Data Index: 986299 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1374132 (Python Code)

Max Activating Token Index: 885

Text #13

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1341355 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1135192 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3225. Min Act: -0.0000

Data Index: 291132 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3399. Min Act: -0.0000

Data Index: 855836 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3289. Min Act: -0.0000

Data Index: 179068 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1594125 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 0.8139. Min Range: -0.8139

Max Act: 0.3210. Min Act: -0.0000

Data Index: 495970 (C4 (Web Text))

Max Activating Token Index: 201