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

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

Neuron 3466 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.8388. Min Act: -0.0001

Data Index: 1424942 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.7140. Min Act: -0.0001

Data Index: 934626 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.6164. Min Act: -0.0001

Data Index: 1561154 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.6791. Min Act: -0.0001

Data Index: 662906 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5776. Min Act: -0.0001

Data Index: 577872 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.6436. Min Act: -0.0001

Data Index: 1095559 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5512. Min Act: -0.0001

Data Index: 113731 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5583. Min Act: -0.0001

Data Index: 1219352 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.6684. Min Act: -0.0001

Data Index: 295513 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.4993. Min Act: -0.0001

Data Index: 685087 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5721. Min Act: -0.0001

Data Index: 1622360 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5130. Min Act: -0.0001

Data Index: 89449 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5223. Min Act: -0.0001

Data Index: 516774 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5864. Min Act: -0.0001

Data Index: 411900 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.4145. Min Act: -0.0001

Data Index: 691684 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.3991. Min Act: -0.0001

Data Index: 48366 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.3829. Min Act: -0.0001

Data Index: 473998 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.5058. Min Act: -0.0001

Data Index: 1534395 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.4675. Min Act: -0.0001

Data Index: 1214962 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.8388. Min Range: -1.8388

Max Act: 1.4644. Min Act: -0.0001

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 839