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

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

Neuron 4513 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.8403. Min Act: -0.0000

Data Index: 371281 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.8802. Min Act: -0.0000

Data Index: 895608 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1229029 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.6375. Min Act: -0.0000

Data Index: 227985 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.6233. Min Act: -0.0000

Data Index: 179327 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.5918. Min Act: -0.0000

Data Index: 452090 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.5225. Min Act: 0.0000

Data Index: 91296 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.5686. Min Act: -0.0000

Data Index: 576508 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.5109. Min Act: -0.0000

Data Index: 131245 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1224175 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1186944 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1330531 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4603. Min Act: -0.0000

Data Index: 64916 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4782. Min Act: -0.0000

Data Index: 287580 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4653. Min Act: -0.0000

Data Index: 477894 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4770. Min Act: -0.0000

Data Index: 739103 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4514. Min Act: -0.0000

Data Index: 396245 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1137848 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4449. Min Act: -0.0000

Data Index: 525646 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.8802. Min Range: -0.8802

Max Act: 0.4439. Min Act: 0.0000

Data Index: 671888 (C4 (Web Text))

Max Activating Token Index: 460