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

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

Neuron 3082 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: 0.7276. Min Range: -0.7276

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1240135 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6248. Min Act: -0.0000

Data Index: 239124 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6072. Min Act: -0.0000

Data Index: 389506 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6220. Min Act: -0.0000

Data Index: 160397 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.6261. Min Act: -0.0000

Data Index: 997164 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5592. Min Act: -0.0000

Data Index: 321679 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5751. Min Act: -0.0000

Data Index: 76899 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5862. Min Act: -0.0000

Data Index: 454378 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5588. Min Act: -0.0000

Data Index: 499410 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1207265 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5795. Min Act: -0.0000

Data Index: 179841 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5774. Min Act: -0.0000

Data Index: 775855 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.5192. Min Act: -0.0000

Data Index: 252373 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4806. Min Act: -0.0000

Data Index: 486481 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4430. Min Act: -0.0000

Data Index: 762983 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1324829 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4475. Min Act: -0.0000

Data Index: 392561 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1318580 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4360. Min Act: -0.0000

Data Index: 899271 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.7276. Min Range: -0.7276

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1344562 (C4 (Web Text))

Max Activating Token Index: 227