Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 325 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0006

Data Index: 297759 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0322. Min Act: -0.0006

Data Index: 281118 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1269998 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1020488 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0319. Min Act: -0.0006

Data Index: 880296 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0315. Min Act: -0.0006

Data Index: 13621 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0301. Min Act: -0.0006

Data Index: 161885 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0299. Min Act: -0.0006

Data Index: 357537 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0301. Min Act: -0.0006

Data Index: 806363 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0294. Min Act: -0.0006

Data Index: 430294 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0300. Min Act: -0.0006

Data Index: 360438 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0299. Min Act: -0.0006

Data Index: 245520 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0284. Min Act: -0.0006

Data Index: 258976 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0288. Min Act: -0.0006

Data Index: 940580 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0275. Min Act: -0.0006

Data Index: 103548 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0267. Min Act: -0.0006

Data Index: 121425 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1347154 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1023649 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1038251 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0277. Min Act: -0.0006

Data Index: 956539 (C4 (Web Text))

Max Activating Token Index: 743