Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1381 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.9831. Min Act: -0.0001

Data Index: 486967 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 6.1894. Min Range: -6.1894

Max Act: 6.1894. Min Act: -0.0001

Data Index: 262334 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 6.1894. Min Range: -6.1894

Max Act: 6.1461. Min Act: -0.0001

Data Index: 1140662 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.4349. Min Act: -0.0001

Data Index: 833231 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 6.1894. Min Range: -6.1894

Max Act: 4.9988. Min Act: -0.0001

Data Index: 1179155 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.1619. Min Act: -0.0001

Data Index: 759826 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 6.1894. Min Range: -6.1894

Max Act: 4.8731. Min Act: -0.0001

Data Index: 36151 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 6.1894. Min Range: -6.1894

Max Act: 4.8168. Min Act: -0.0001

Data Index: 968002 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 6.1894. Min Range: -6.1894

Max Act: 4.8890. Min Act: -0.0001

Data Index: 1355156 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 6.1894. Min Range: -6.1894

Max Act: 3.8475. Min Act: -0.0001

Data Index: 1211491 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 6.1894. Min Range: -6.1894

Max Act: 4.2556. Min Act: -0.0002

Data Index: 1022557 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 6.1894. Min Range: -6.1894

Max Act: 3.9408. Min Act: -0.0001

Data Index: 720026 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 6.1894. Min Range: -6.1894

Max Act: 3.7499. Min Act: -0.0001

Data Index: 832532 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 6.1894. Min Range: -6.1894

Max Act: 2.8958. Min Act: -0.0001

Data Index: 313641 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 6.1894. Min Range: -6.1894

Max Act: 2.8484. Min Act: -0.0002

Data Index: 872993 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 6.1894. Min Range: -6.1894

Max Act: 3.1470. Min Act: -0.0001

Data Index: 51597 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 6.1894. Min Range: -6.1894

Max Act: 3.0660. Min Act: -0.0001

Data Index: 956169 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 6.1894. Min Range: -6.1894

Max Act: 3.0390. Min Act: -0.0001

Data Index: 132129 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 6.1894. Min Range: -6.1894

Max Act: 2.8929. Min Act: -0.0001

Data Index: 342175 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 6.1894. Min Range: -6.1894

Max Act: 2.6940. Min Act: -0.0001

Data Index: 934661 (C4 (Web Text))

Max Activating Token Index: 184