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

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

Neuron 668 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5782. Min Act: -0.0000

Data Index: 756770 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.6095. Min Act: -0.0000

Data Index: 967915 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1131449 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5847. Min Act: -0.0000

Data Index: 581521 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.6038. Min Act: -0.0000

Data Index: 793708 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1280855 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1215805 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5714. Min Act: -0.0000

Data Index: 9556 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5700. Min Act: -0.0000

Data Index: 817416 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1044056 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1127326 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5406. Min Act: -0.0000

Data Index: 744183 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5176. Min Act: -0.0000

Data Index: 997911 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1049766 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5121. Min Act: -0.0000

Data Index: 563233 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1225349 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4860. Min Act: -0.0000

Data Index: 310161 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.5322. Min Act: -0.0000

Data Index: 367806 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4964. Min Act: -0.0000

Data Index: 754206 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.6095. Min Range: -0.6095

Max Act: 0.4547. Min Act: -0.0000

Data Index: 840952 (C4 (Web Text))

Max Activating Token Index: 299