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

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

Neuron 2147 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: 2.1411. Min Range: -2.1411

Max Act: 2.1411. Min Act: -0.0002

Data Index: 792637 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.7829. Min Act: -0.0002

Data Index: 321935 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.7063. Min Act: -0.0002

Data Index: 510224 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.7320. Min Act: -0.0002

Data Index: 753216 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.6985. Min Act: -0.0002

Data Index: 458312 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.6442. Min Act: -0.0002

Data Index: 629698 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.6749. Min Act: -0.0002

Data Index: 485004 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.5655. Min Act: -0.0002

Data Index: 1071094 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.5958. Min Act: -0.0002

Data Index: 1160264 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.5923. Min Act: -0.0002

Data Index: 211579 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.5177. Min Act: -0.0002

Data Index: 1103827 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.5409. Min Act: -0.0002

Data Index: 213973 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.4757. Min Act: -0.0002

Data Index: 37798 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.5488. Min Act: -0.0002

Data Index: 1112212 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.4841. Min Act: -0.0002

Data Index: 172266 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.4793. Min Act: -0.0002

Data Index: 422550 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.4691. Min Act: -0.0002

Data Index: 703424 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.4425. Min Act: -0.0002

Data Index: 1165908 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.4410. Min Act: -0.0002

Data Index: 641002 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.1411. Min Range: -2.1411

Max Act: 1.4371. Min Act: -0.0002

Data Index: 1235879 (C4 (Web Text))

Max Activating Token Index: 627