Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2846 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4881. Min Act: -0.0001

Data Index: 15074 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4536. Min Act: -0.0001

Data Index: 1014344 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4148. Min Act: -0.0001

Data Index: 1338033 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4281. Min Act: -0.0001

Data Index: 421049 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3704. Min Act: -0.0001

Data Index: 555290 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3567. Min Act: -0.0001

Data Index: 68640 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1274726 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3593. Min Act: -0.0001

Data Index: 555992 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3397. Min Act: -0.0001

Data Index: 562736 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3230. Min Act: -0.0001

Data Index: 981085 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3138. Min Act: -0.0001

Data Index: 918650 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3105. Min Act: -0.0001

Data Index: 1194552 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1231693 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3222. Min Act: -0.0001

Data Index: 210562 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3103. Min Act: -0.0001

Data Index: 889821 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3090. Min Act: -0.0001

Data Index: 960714 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.2975. Min Act: -0.0001

Data Index: 597179 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3037. Min Act: -0.0001

Data Index: 535165 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.2911. Min Act: -0.0001

Data Index: 198246 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.2981. Min Act: -0.0001

Data Index: 1044275 (C4 (Web Text))

Max Activating Token Index: 618