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

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

Neuron 5681 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.4120. Min Act: -0.0000

Data Index: 1497365 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.1660. Min Act: -0.0000

Data Index: 1614892 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.3293. Min Act: -0.0000

Data Index: 1512684 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.2911. Min Act: -0.0000

Data Index: 1490153 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.1607. Min Act: -0.0000

Data Index: 1470699 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9684. Min Act: -0.0000

Data Index: 1515752 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9829. Min Act: -0.0000

Data Index: 1529381 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.1554. Min Act: -0.0000

Data Index: 1511042 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9737. Min Act: -0.0000

Data Index: 1572063 (Python Code)

Max Activating Token Index: 590

Text #9

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.1460. Min Act: -0.0000

Data Index: 1360965 (Python Code)

Max Activating Token Index: 653

Text #10

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.1082. Min Act: -0.0000

Data Index: 1455032 (Python Code)

Max Activating Token Index: 768

Text #11

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9272. Min Act: -0.0000

Data Index: 1367036 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.2527. Min Act: -0.0000

Data Index: 1385643 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.0076. Min Act: -0.0000

Data Index: 1453480 (Python Code)

Max Activating Token Index: 575

Text #14

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9652. Min Act: -0.0000

Data Index: 1440020 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9728. Min Act: -0.0000

Data Index: 1528347 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 4.4120. Min Range: -4.4120

Max Act: 4.1242. Min Act: -0.0000

Data Index: 1410525 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9371. Min Act: -0.0000

Data Index: 1369066 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.9528. Min Act: -0.0000

Data Index: 1457745 (Python Code)

Max Activating Token Index: 353

Text #19

Max Range: 4.4120. Min Range: -4.4120

Max Act: 3.7606. Min Act: -0.0000

Data Index: 1423132 (Python Code)

Max Activating Token Index: 155