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

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

Neuron 2992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.9246. Min Act: -0.0002

Data Index: 48640 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.9190. Min Act: -0.0002

Data Index: 1088554 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.8719. Min Act: -0.0002

Data Index: 524130 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.8162. Min Act: -0.0002

Data Index: 640030 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.8641. Min Act: -0.0002

Data Index: 732648 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.7133. Min Act: -0.0002

Data Index: 877458 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.6446. Min Act: -0.0002

Data Index: 1339937 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.6512. Min Act: -0.0002

Data Index: 110985 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.6719. Min Act: -0.0002

Data Index: 127605 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.6320. Min Act: -0.0002

Data Index: 452433 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.5200. Min Act: -0.0002

Data Index: 352416 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.5637. Min Act: -0.0002

Data Index: 1349515 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.5813. Min Act: -0.0002

Data Index: 355462 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.5729. Min Act: -0.0002

Data Index: 1298679 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.5288. Min Act: -0.0002

Data Index: 231413 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.4818. Min Act: -0.0002

Data Index: 340733 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.4440. Min Act: -0.0002

Data Index: 229057 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.4657. Min Act: -0.0003

Data Index: 261099 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.4764. Min Act: -0.0002

Data Index: 1278158 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 2.9246. Min Range: -2.9246

Max Act: 2.3877. Min Act: -0.0002

Data Index: 613680 (C4 (Web Text))

Max Activating Token Index: 144