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

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

Neuron 2482 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2894. Min Act: -0.0001

Data Index: 841338 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2548. Min Act: -0.0001

Data Index: 473171 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2581. Min Act: -0.0001

Data Index: 31943 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2463. Min Act: -0.0001

Data Index: 1334098 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2176. Min Act: -0.0001

Data Index: 580513 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2069. Min Act: -0.0001

Data Index: 1334449 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2207. Min Act: -0.0001

Data Index: 12488 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1971. Min Act: -0.0001

Data Index: 712117 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1919. Min Act: -0.0002

Data Index: 921554 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2048. Min Act: -0.0001

Data Index: 1097137 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2098. Min Act: -0.0001

Data Index: 319731 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1882. Min Act: -0.0001

Data Index: 795649 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1923. Min Act: -0.0001

Data Index: 410938 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1931. Min Act: -0.0002

Data Index: 704882 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.2026. Min Act: -0.0002

Data Index: 254837 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1755. Min Act: -0.0001

Data Index: 726200 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1622. Min Act: -0.0001

Data Index: 250487 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1613. Min Act: -0.0001

Data Index: 1255191 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1708. Min Act: -0.0001

Data Index: 31041 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.2894. Min Range: -1.2894

Max Act: 1.1506. Min Act: -0.0001

Data Index: 683308 (C4 (Web Text))

Max Activating Token Index: 60