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

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

Neuron 2300 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0467. Min Range: -4.0467

Max Act: 4.0467. Min Act: -0.0001

Data Index: 189159 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.8866. Min Act: -0.0000

Data Index: 163065 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.6526. Min Act: -0.0000

Data Index: 11018 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.6292. Min Act: -0.0001

Data Index: 224911 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.6203. Min Act: -0.0001

Data Index: 378261 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.5550. Min Act: -0.0001

Data Index: 339708 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.5354. Min Act: -0.0000

Data Index: 681870 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3349. Min Act: -0.0001

Data Index: 187262 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3334. Min Act: -0.0001

Data Index: 873741 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.6269. Min Act: -0.0001

Data Index: 815405 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2946. Min Act: -0.0000

Data Index: 128882 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.4200. Min Act: -0.0001

Data Index: 441468 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3901. Min Act: -0.0000

Data Index: 292758 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.1801. Min Act: -0.0001

Data Index: 77981 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.6346. Min Act: -0.0000

Data Index: 237540 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3111. Min Act: -0.0001

Data Index: 1160470 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.3022. Min Act: -0.0001

Data Index: 1149513 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2654. Min Act: -0.0001

Data Index: 604422 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.0798. Min Act: -0.0001

Data Index: 570288 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 4.0467. Min Range: -4.0467

Max Act: 3.2170. Min Act: -0.0001

Data Index: 191729 (C4 (Web Text))

Max Activating Token Index: 693