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

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

Neuron 895 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.9858. Min Act: -0.0000

Data Index: 1565445 (Python Code)

Max Activating Token Index: 343

Text #1

Max Range: 3.0572. Min Range: -3.0572

Max Act: 3.0572. Min Act: -0.0000

Data Index: 1366360 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.7077. Min Act: -0.0000

Data Index: 1386757 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.6718. Min Act: -0.0000

Data Index: 1427192 (Python Code)

Max Activating Token Index: 792

Text #4

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.7477. Min Act: -0.0000

Data Index: 1360557 (Python Code)

Max Activating Token Index: 938

Text #5

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.4318. Min Act: -0.0000

Data Index: 1456158 (Python Code)

Max Activating Token Index: 652

Text #6

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.3999. Min Act: -0.0000

Data Index: 1612669 (Python Code)

Max Activating Token Index: 516

Text #7

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.3138. Min Act: -0.0000

Data Index: 702752 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.2976. Min Act: -0.0000

Data Index: 1452015 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.2917. Min Act: -0.0000

Data Index: 1543598 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.2925. Min Act: -0.0000

Data Index: 1600622 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.1411. Min Act: -0.0000

Data Index: 1364489 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0906. Min Act: -0.0000

Data Index: 1366628 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.2180. Min Act: -0.0000

Data Index: 1580741 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0796. Min Act: -0.0000

Data Index: 442350 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0327. Min Act: -0.0000

Data Index: 1009730 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0136. Min Act: -0.0000

Data Index: 1371293 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1570193 (Python Code)

Max Activating Token Index: 774

Text #18

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.0341. Min Act: -0.0000

Data Index: 1486557 (Python Code)

Max Activating Token Index: 289

Text #19

Max Range: 3.0572. Min Range: -3.0572

Max Act: 2.1445. Min Act: -0.0000

Data Index: 1623005 (Python Code)

Max Activating Token Index: 979