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

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

Neuron 3423 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: 2.1795. Min Range: -2.1795

Max Act: 2.1795. Min Act: 0.0000

Data Index: 590414 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.7321. Min Act: -0.0000

Data Index: 525627 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.6652. Min Act: -0.0000

Data Index: 660567 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.5504. Min Act: -0.0000

Data Index: 600857 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.3560. Min Act: -0.0000

Data Index: 220371 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.4738. Min Act: -0.0000

Data Index: 1153582 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.3869. Min Act: -0.0000

Data Index: 950314 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1195575 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.3512. Min Act: -0.0000

Data Index: 641264 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.4235. Min Act: -0.0000

Data Index: 808498 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.3005. Min Act: -0.0000

Data Index: 410946 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1071563 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.1642. Min Act: -0.0000

Data Index: 1020186 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.1709. Min Act: -0.0000

Data Index: 494909 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.2456. Min Act: -0.0000

Data Index: 521204 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.1604. Min Act: -0.0000

Data Index: 856609 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1307564 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.2723. Min Act: -0.0000

Data Index: 321238 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.1710. Min Act: -0.0000

Data Index: 906811 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 2.1795. Min Range: -2.1795

Max Act: 1.1371. Min Act: -0.0000

Data Index: 946058 (C4 (Web Text))

Max Activating Token Index: 279