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

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

Neuron 4121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.6650. Min Act: -0.0000

Data Index: 1013948 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.7070. Min Act: -0.0000

Data Index: 796578 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.5562. Min Act: -0.0000

Data Index: 430107 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.3819. Min Act: -0.0000

Data Index: 1225698 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.5239. Min Act: -0.0000

Data Index: 254842 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.2403. Min Act: -0.0000

Data Index: 230148 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.3685. Min Act: -0.0000

Data Index: 80110 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.3287. Min Act: -0.0000

Data Index: 1045392 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.3157. Min Act: -0.0000

Data Index: 833053 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.3229. Min Act: -0.0000

Data Index: 334314 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.2361. Min Act: -0.0000

Data Index: 170331 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.1168. Min Act: -0.0000

Data Index: 695161 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.0998. Min Act: -0.0000

Data Index: 494947 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.2337. Min Act: -0.0000

Data Index: 666674 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.1646. Min Act: -0.0000

Data Index: 381773 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.3175. Min Act: -0.0000

Data Index: 669023 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.1622. Min Act: -0.0000

Data Index: 172744 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.0408. Min Act: -0.0000

Data Index: 1156372 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.1451. Min Act: -0.0000

Data Index: 1330238 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 2.7070. Min Range: -2.7070

Max Act: 2.1199. Min Act: -0.0000

Data Index: 1115746 (C4 (Web Text))

Max Activating Token Index: 208