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

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

Neuron 2103 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: 3.8178. Min Range: -3.8178

Max Act: 3.8178. Min Act: -0.0000

Data Index: 1451882 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 3.8178. Min Range: -3.8178

Max Act: 3.2128. Min Act: -0.0000

Data Index: 1483880 (Python Code)

Max Activating Token Index: 925

Text #2

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.7495. Min Act: -0.0000

Data Index: 1041156 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 3.8178. Min Range: -3.8178

Max Act: 3.0470. Min Act: -0.0000

Data Index: 743557 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.9559. Min Act: -0.0000

Data Index: 1648178 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.7740. Min Act: -0.0000

Data Index: 1615649 (Python Code)

Max Activating Token Index: 604

Text #6

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.7997. Min Act: -0.0000

Data Index: 1343095 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.8938. Min Act: -0.0000

Data Index: 1518276 (Python Code)

Max Activating Token Index: 257

Text #8

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.4178. Min Act: -0.0000

Data Index: 1360097 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.6304. Min Act: -0.0000

Data Index: 477498 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.3940. Min Act: -0.0000

Data Index: 113107 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.3685. Min Act: -0.0000

Data Index: 715954 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.2443. Min Act: -0.0000

Data Index: 521748 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.3648. Min Act: -0.0000

Data Index: 958560 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.3845. Min Act: -0.0000

Data Index: 614146 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.5689. Min Act: -0.0000

Data Index: 241211 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.4437. Min Act: -0.0000

Data Index: 1114745 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.3229. Min Act: -0.0000

Data Index: 302497 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.5532. Min Act: -0.0000

Data Index: 473696 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 3.8178. Min Range: -3.8178

Max Act: 2.4388. Min Act: -0.0000

Data Index: 1604559 (Python Code)

Max Activating Token Index: 1007