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

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

Neuron 107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9844. Min Range: -5.9844

Max Act: 5.9844. Min Act: -0.0000

Data Index: 97492 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 5.9844. Min Range: -5.9844

Max Act: 5.4893. Min Act: -0.0000

Data Index: 803241 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 5.9844. Min Range: -5.9844

Max Act: 5.4324. Min Act: -0.0000

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 5.9844. Min Range: -5.9844

Max Act: 5.3177. Min Act: -0.0000

Data Index: 547007 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 5.9844. Min Range: -5.9844

Max Act: 5.2471. Min Act: -0.0000

Data Index: 557794 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 5.9844. Min Range: -5.9844

Max Act: 5.0279. Min Act: -0.0000

Data Index: 541433 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.9500. Min Act: -0.0000

Data Index: 852753 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.6397. Min Act: -0.0000

Data Index: 1103506 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.6450. Min Act: -0.0000

Data Index: 140940 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.1336. Min Act: -0.0000

Data Index: 223598 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.7287. Min Act: -0.0000

Data Index: 1125624 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.2596. Min Act: -0.0001

Data Index: 1220692 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.6707. Min Act: -0.0000

Data Index: 585191 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 5.9844. Min Range: -5.9844

Max Act: 3.8682. Min Act: -0.0000

Data Index: 1068544 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.1747. Min Act: -0.0000

Data Index: 1201953 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.1957. Min Act: -0.0000

Data Index: 1335981 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.0283. Min Act: -0.0000

Data Index: 14137 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.2529. Min Act: -0.0000

Data Index: 923618 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.3588. Min Act: -0.0000

Data Index: 1321710 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 5.9844. Min Range: -5.9844

Max Act: 4.0498. Min Act: -0.0000

Data Index: 1194675 (C4 (Web Text))

Max Activating Token Index: 927