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

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

Neuron 2893 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: 6.6179. Min Range: -6.6179

Max Act: 6.6179. Min Act: -0.0000

Data Index: 976991 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 6.6179. Min Range: -6.6179

Max Act: 6.0678. Min Act: -0.0000

Data Index: 1063958 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 6.6179. Min Range: -6.6179

Max Act: 5.7335. Min Act: -0.0000

Data Index: 450960 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 6.6179. Min Range: -6.6179

Max Act: 5.2933. Min Act: -0.0000

Data Index: 854826 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 6.6179. Min Range: -6.6179

Max Act: 5.2658. Min Act: -0.0000

Data Index: 987318 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 6.6179. Min Range: -6.6179

Max Act: 5.3160. Min Act: -0.0000

Data Index: 1033439 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 6.6179. Min Range: -6.6179

Max Act: 4.8033. Min Act: -0.0000

Data Index: 1252213 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 6.6179. Min Range: -6.6179

Max Act: 4.5524. Min Act: -0.0000

Data Index: 157120 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 6.6179. Min Range: -6.6179

Max Act: 4.3813. Min Act: -0.0000

Data Index: 244441 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 6.6179. Min Range: -6.6179

Max Act: 3.6351. Min Act: -0.0000

Data Index: 1289515 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 6.6179. Min Range: -6.6179

Max Act: 3.6827. Min Act: -0.0000

Data Index: 443924 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 6.6179. Min Range: -6.6179

Max Act: 3.3593. Min Act: -0.0000

Data Index: 860145 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.6206. Min Act: -0.0000

Data Index: 91233 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.5215. Min Act: -0.0000

Data Index: 1102627 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.4273. Min Act: -0.0000

Data Index: 493508 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.3866. Min Act: -0.0000

Data Index: 65204 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.2244. Min Act: -0.0000

Data Index: 214021 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.3116. Min Act: -0.0000

Data Index: 1278786 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.2749. Min Act: -0.0000

Data Index: 1006694 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 6.6179. Min Range: -6.6179

Max Act: 2.2477. Min Act: -0.0000

Data Index: 794315 (C4 (Web Text))

Max Activating Token Index: 126