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

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

Neuron 1678 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: 1.4057. Min Range: -1.4057

Max Act: 1.4057. Min Act: -0.0002

Data Index: 891326 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.3161. Min Act: -0.0002

Data Index: 437439 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.3076. Min Act: -0.0002

Data Index: 713574 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2936. Min Act: -0.0002

Data Index: 721324 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2928. Min Act: -0.0002

Data Index: 87614 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2589. Min Act: -0.0002

Data Index: 79548 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2138. Min Act: -0.0002

Data Index: 82721 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2536. Min Act: -0.0002

Data Index: 891462 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2654. Min Act: -0.0002

Data Index: 1161325 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2595. Min Act: -0.0002

Data Index: 669462 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2341. Min Act: -0.0002

Data Index: 1158058 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2504. Min Act: -0.0002

Data Index: 623318 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2896. Min Act: -0.0002

Data Index: 91221 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2514. Min Act: -0.0003

Data Index: 812593 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2212. Min Act: -0.0002

Data Index: 761526 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2401. Min Act: -0.0002

Data Index: 615063 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2231. Min Act: -0.0002

Data Index: 1003691 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.1969. Min Act: -0.0002

Data Index: 416510 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2447. Min Act: -0.0002

Data Index: 621839 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 1.4057. Min Range: -1.4057

Max Act: 1.2192. Min Act: -0.0002

Data Index: 492390 (C4 (Web Text))

Max Activating Token Index: 480