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

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

Neuron 4143 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9967. Min Act: -0.0002

Data Index: 573992 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8430. Min Act: -0.0002

Data Index: 324957 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9219. Min Act: -0.0002

Data Index: 448748 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9290. Min Act: -0.0002

Data Index: 611848 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9087. Min Act: -0.0002

Data Index: 231231 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8970. Min Act: -0.0002

Data Index: 915199 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.9021. Min Act: -0.0002

Data Index: 468486 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8923. Min Act: -0.0002

Data Index: 461014 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8837. Min Act: -0.0002

Data Index: 1078550 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.7334. Min Act: -0.0002

Data Index: 208451 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8025. Min Act: -0.0002

Data Index: 810006 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.7936. Min Act: -0.0002

Data Index: 1161396 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8219. Min Act: -0.0002

Data Index: 546705 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8193. Min Act: -0.0002

Data Index: 529216 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8518. Min Act: -0.0002

Data Index: 211251 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.7875. Min Act: -0.0002

Data Index: 1330061 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.7883. Min Act: -0.0002

Data Index: 779490 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.8378. Min Act: -0.0002

Data Index: 1104028 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.7698. Min Act: -0.0002

Data Index: 866665 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.9967. Min Range: -0.9967

Max Act: 0.7706. Min Act: -0.0002

Data Index: 1010685 (C4 (Web Text))

Max Activating Token Index: 129