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

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

Neuron 3141 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: 4.3743. Min Range: -4.3743

Max Act: 4.3743. Min Act: -0.0000

Data Index: 117702 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 4.3743. Min Range: -4.3743

Max Act: 4.1688. Min Act: -0.0000

Data Index: 794669 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.9941. Min Act: -0.0000

Data Index: 1331661 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.7632. Min Act: -0.0000

Data Index: 1041774 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.8602. Min Act: -0.0000

Data Index: 48518 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.5006. Min Act: -0.0000

Data Index: 1257021 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.7534. Min Act: -0.0000

Data Index: 593652 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.4281. Min Act: -0.0000

Data Index: 876932 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.6696. Min Act: -0.0000

Data Index: 421664 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.3436. Min Act: -0.0000

Data Index: 736098 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.4831. Min Act: -0.0000

Data Index: 1155175 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.4082. Min Act: -0.0000

Data Index: 452496 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.0048. Min Act: -0.0000

Data Index: 156535 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.5870. Min Act: -0.0000

Data Index: 388542 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.2468. Min Act: 0.0000

Data Index: 361501 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.3506. Min Act: -0.0000

Data Index: 255571 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.2227. Min Act: -0.0000

Data Index: 420797 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.3594. Min Act: -0.0000

Data Index: 1125705 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 4.3743. Min Range: -4.3743

Max Act: 3.1572. Min Act: -0.0000

Data Index: 1199024 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 4.3743. Min Range: -4.3743

Max Act: 2.9341. Min Act: -0.0000

Data Index: 558862 (C4 (Web Text))

Max Activating Token Index: 579