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

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

Neuron 2661 in Layer 1

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: 2.9839. Min Range: -2.9839

Max Act: 2.9839. Min Act: -0.0002

Data Index: 391782 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.8707. Min Act: -0.0002

Data Index: 1313786 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.7055. Min Act: -0.0002

Data Index: 1015893 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.5585. Min Act: -0.0002

Data Index: 194161 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.5632. Min Act: -0.0002

Data Index: 146036 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.4820. Min Act: -0.0002

Data Index: 1208337 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.5264. Min Act: -0.0002

Data Index: 902802 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.4689. Min Act: -0.0002

Data Index: 905128 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.3564. Min Act: -0.0002

Data Index: 562009 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.3372. Min Act: -0.0002

Data Index: 313673 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.2653. Min Act: -0.0002

Data Index: 438505 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.1968. Min Act: -0.0002

Data Index: 1283304 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.1809. Min Act: -0.0002

Data Index: 1073698 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.1664. Min Act: -0.0002

Data Index: 251169 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.0987. Min Act: -0.0002

Data Index: 1296002 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.1154. Min Act: -0.0002

Data Index: 1012900 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.0593. Min Act: -0.0003

Data Index: 629712 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.1062. Min Act: -0.0002

Data Index: 975318 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.0813. Min Act: -0.0002

Data Index: 540556 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 2.9839. Min Range: -2.9839

Max Act: 2.0716. Min Act: -0.0002

Data Index: 65670 (C4 (Web Text))

Max Activating Token Index: 951