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

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

Neuron 3450 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: 2.2288. Min Range: -2.2288

Max Act: 2.2288. Min Act: -0.0000

Data Index: 1194951 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 2.2288. Min Range: -2.2288

Max Act: 2.2123. Min Act: -0.0000

Data Index: 78099 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.9945. Min Act: -0.0000

Data Index: 482253 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 2.2288. Min Range: -2.2288

Max Act: 2.1229. Min Act: -0.0000

Data Index: 1018725 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.2288. Min Range: -2.2288

Max Act: 2.0669. Min Act: -0.0000

Data Index: 758974 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.2288. Min Range: -2.2288

Max Act: 2.0282. Min Act: -0.0000

Data Index: 1494246 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.8806. Min Act: -0.0000

Data Index: 597681 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 2.2288. Min Range: -2.2288

Max Act: 2.0443. Min Act: -0.0000

Data Index: 774780 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.7904. Min Act: -0.0000

Data Index: 1442523 (Python Code)

Max Activating Token Index: 868

Text #9

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.8693. Min Act: -0.0000

Data Index: 593561 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.9649. Min Act: -0.0000

Data Index: 1561731 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.7325. Min Act: -0.0000

Data Index: 415312 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.7693. Min Act: -0.0000

Data Index: 903634 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1619258 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.6535. Min Act: -0.0000

Data Index: 1555918 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1191557 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.7525. Min Act: -0.0000

Data Index: 1196805 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.6388. Min Act: -0.0000

Data Index: 1252208 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.7482. Min Act: -0.0000

Data Index: 957755 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 2.2288. Min Range: -2.2288

Max Act: 1.6839. Min Act: -0.0000

Data Index: 1464029 (Python Code)

Max Activating Token Index: 61