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

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

Neuron 1554 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.9489. Min Act: -0.0000

Data Index: 1483150 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.9580. Min Act: -0.0000

Data Index: 1411278 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.7507. Min Act: -0.0000

Data Index: 1604956 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.7831. Min Act: -0.0000

Data Index: 1543276 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.2397. Min Act: -0.0000

Data Index: 1386512 (Python Code)

Max Activating Token Index: 573

Text #5

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.5584. Min Act: -0.0000

Data Index: 1412424 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.1345. Min Act: -0.0000

Data Index: 1405466 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.1915. Min Act: -0.0000

Data Index: 1504949 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.1593. Min Act: -0.0000

Data Index: 1497977 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.0778. Min Act: -0.0000

Data Index: 1644784 (Python Code)

Max Activating Token Index: 750

Text #10

Max Range: 6.9580. Min Range: -6.9580

Max Act: 5.9936. Min Act: -0.0000

Data Index: 1365691 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 6.9580. Min Range: -6.9580

Max Act: 5.6766. Min Act: -0.0000

Data Index: 1536987 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 6.9580. Min Range: -6.9580

Max Act: 6.1637. Min Act: -0.0000

Data Index: 1578949 (Python Code)

Max Activating Token Index: 1005

Text #13

Max Range: 6.9580. Min Range: -6.9580

Max Act: 5.6528. Min Act: -0.0000

Data Index: 1656680 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 6.9580. Min Range: -6.9580

Max Act: 5.9966. Min Act: -0.0000

Data Index: 1622565 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 6.9580. Min Range: -6.9580

Max Act: 5.5623. Min Act: -0.0000

Data Index: 1540167 (Python Code)

Max Activating Token Index: 599

Text #16

Max Range: 6.9580. Min Range: -6.9580

Max Act: 5.5134. Min Act: -0.0000

Data Index: 1393490 (Python Code)

Max Activating Token Index: 850

Text #17

Max Range: 6.9580. Min Range: -6.9580

Max Act: 4.9450. Min Act: -0.0000

Data Index: 1401635 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 6.9580. Min Range: -6.9580

Max Act: 5.3074. Min Act: -0.0000

Data Index: 1551517 (Python Code)

Max Activating Token Index: 407

Text #19

Max Range: 6.9580. Min Range: -6.9580

Max Act: 4.7855. Min Act: -0.0000

Data Index: 1468626 (Python Code)

Max Activating Token Index: 201