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

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

Neuron 3595 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.1793. Min Act: -0.0000

Data Index: 619104 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 2.1793. Min Range: -2.1793

Max Act: 2.0800. Min Act: -0.0000

Data Index: 1218191 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9703. Min Act: -0.0000

Data Index: 297354 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.9186. Min Act: -0.0000

Data Index: 448698 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8176. Min Act: -0.0000

Data Index: 823029 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.8059. Min Act: -0.0000

Data Index: 452910 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1277840 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.6314. Min Act: -0.0000

Data Index: 1315791 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.6398. Min Act: -0.0000

Data Index: 951533 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.5014. Min Act: -0.0000

Data Index: 736534 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1236934 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.5280. Min Act: -0.0000

Data Index: 134720 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.5395. Min Act: -0.0000

Data Index: 1056934 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1342992 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.2907. Min Act: -0.0000

Data Index: 459391 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.4512. Min Act: -0.0000

Data Index: 1153866 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1064013 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.4292. Min Act: -0.0000

Data Index: 166613 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.3893. Min Act: -0.0000

Data Index: 872163 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 2.1793. Min Range: -2.1793

Max Act: 1.3397. Min Act: -0.0000

Data Index: 411799 (C4 (Web Text))

Max Activating Token Index: 758