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

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

Neuron 3025 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0392. Min Range: -1.0392

Max Act: 1.0392. Min Act: -0.0000

Data Index: 684279 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1332917 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1489502 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.8454. Min Act: -0.0001

Data Index: 1482432 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.8117. Min Act: -0.0000

Data Index: 12429 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7463. Min Act: -0.0001

Data Index: 1242110 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7928. Min Act: -0.0001

Data Index: 1622946 (Python Code)

Max Activating Token Index: 967

Text #7

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1435093 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7649. Min Act: -0.0000

Data Index: 426416 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1001534 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7667. Min Act: -0.0000

Data Index: 720616 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7122. Min Act: -0.0000

Data Index: 843049 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7466. Min Act: -0.0000

Data Index: 34442 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7586. Min Act: -0.0000

Data Index: 115954 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1421845 (Python Code)

Max Activating Token Index: 192

Text #15

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7090. Min Act: -0.0000

Data Index: 665249 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7432. Min Act: -0.0001

Data Index: 1365969 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7241. Min Act: -0.0000

Data Index: 694423 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7674. Min Act: -0.0000

Data Index: 67650 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.0392. Min Range: -1.0392

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1215027 (C4 (Web Text))

Max Activating Token Index: 706