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

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

Neuron 3701 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.4570. Min Act: -0.0000

Data Index: 1254015 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.3140. Min Act: -0.0000

Data Index: 158944 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.1969. Min Act: -0.0000

Data Index: 690755 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.2588. Min Act: -0.0000

Data Index: 112456 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.1330. Min Act: -0.0000

Data Index: 387100 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.1044. Min Act: 0.0000

Data Index: 1292700 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.1025. Min Act: -0.0000

Data Index: 39501 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.9944. Min Act: -0.0000

Data Index: 796484 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.0706. Min Act: -0.0000

Data Index: 712104 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.9014. Min Act: -0.0000

Data Index: 1213978 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.9801. Min Act: -0.0000

Data Index: 444908 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.8331. Min Act: -0.0000

Data Index: 1254222 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.4570. Min Range: -2.4570

Max Act: 2.0181. Min Act: -0.0000

Data Index: 1231443 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.8849. Min Act: -0.0000

Data Index: 33224 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.9738. Min Act: -0.0000

Data Index: 1071538 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1120111 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.8522. Min Act: -0.0000

Data Index: 1110447 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.7351. Min Act: -0.0000

Data Index: 702011 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.8212. Min Act: -0.0000

Data Index: 289807 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.4570. Min Range: -2.4570

Max Act: 1.8163. Min Act: -0.0000

Data Index: 451068 (C4 (Web Text))

Max Activating Token Index: 636