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

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

Neuron 2129 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6334. Min Act: -0.0001

Data Index: 639003 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6232. Min Act: -0.0001

Data Index: 171687 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5216. Min Act: -0.0000

Data Index: 949253 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5820. Min Act: -0.0001

Data Index: 193513 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5521. Min Act: -0.0000

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4893. Min Act: -0.0000

Data Index: 928369 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1115133 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5210. Min Act: -0.0001

Data Index: 998565 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5120. Min Act: -0.0000

Data Index: 853271 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4914. Min Act: -0.0000

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4733. Min Act: -0.0000

Data Index: 503549 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4759. Min Act: -0.0000

Data Index: 786396 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4416. Min Act: -0.0000

Data Index: 290286 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4870. Min Act: -0.0000

Data Index: 900918 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1200443 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5009. Min Act: -0.0000

Data Index: 816807 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4829. Min Act: -0.0000

Data Index: 157549 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4777. Min Act: -0.0000

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4791. Min Act: -0.0000

Data Index: 578025 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1351975 (C4 (Web Text))

Max Activating Token Index: 43