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

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

Neuron 5435 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5858. Min Range: -2.5858

Max Act: 2.5858. Min Act: -0.0000

Data Index: 622269 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 2.5858. Min Range: -2.5858

Max Act: 2.3304. Min Act: -0.0000

Data Index: 687578 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.9250. Min Act: -0.0000

Data Index: 356510 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.8896. Min Act: -0.0000

Data Index: 771055 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1328582 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.7700. Min Act: -0.0000

Data Index: 928885 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1206058 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.5799. Min Act: -0.0000

Data Index: 438176 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.5154. Min Act: -0.0000

Data Index: 439087 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.5714. Min Act: -0.0000

Data Index: 762751 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1304010 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.4501. Min Act: -0.0000

Data Index: 153909 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1188205 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.3356. Min Act: -0.0000

Data Index: 989873 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1067025 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.5934. Min Act: -0.0000

Data Index: 944439 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.4723. Min Act: -0.0000

Data Index: 979027 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1121962 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.5354. Min Act: -0.0000

Data Index: 965795 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 2.5858. Min Range: -2.5858

Max Act: 1.4149. Min Act: -0.0000

Data Index: 595336 (C4 (Web Text))

Max Activating Token Index: 254