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

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

Neuron 3505 in Layer 0

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: 0.4913. Min Range: -0.4913

Max Act: 0.4913. Min Act: -0.0001

Data Index: 367132 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4729. Min Act: -0.0001

Data Index: 112290 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4728. Min Act: -0.0001

Data Index: 992213 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1095988 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4749. Min Act: -0.0001

Data Index: 675776 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4778. Min Act: -0.0001

Data Index: 464771 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4765. Min Act: -0.0001

Data Index: 83435 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4715. Min Act: -0.0001

Data Index: 630480 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4593. Min Act: -0.0001

Data Index: 638560 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4527. Min Act: -0.0001

Data Index: 706410 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4583. Min Act: -0.0001

Data Index: 1078820 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4228. Min Act: -0.0001

Data Index: 897048 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4329. Min Act: -0.0001

Data Index: 932099 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4218. Min Act: -0.0001

Data Index: 231983 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4291. Min Act: -0.0001

Data Index: 625880 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4181. Min Act: -0.0001

Data Index: 933251 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4197. Min Act: -0.0001

Data Index: 1289764 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1001763 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4120. Min Act: -0.0001

Data Index: 783598 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4154. Min Act: -0.0001

Data Index: 1276206 (C4 (Web Text))

Max Activating Token Index: 500