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

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

Neuron 4133 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: 1.6226. Min Range: -1.6226

Max Act: 1.5911. Min Act: -0.0000

Data Index: 549149 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.5354. Min Act: -0.0000

Data Index: 1187932 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.5003. Min Act: -0.0000

Data Index: 638742 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.5753. Min Act: -0.0000

Data Index: 959092 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.6226. Min Act: -0.0000

Data Index: 182908 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.5277. Min Act: -0.0000

Data Index: 471127 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.5065. Min Act: -0.0000

Data Index: 672764 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.4181. Min Act: -0.0000

Data Index: 331789 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.4243. Min Act: -0.0000

Data Index: 115803 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3908. Min Act: -0.0000

Data Index: 625513 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3733. Min Act: -0.0000

Data Index: 160177 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3880. Min Act: -0.0000

Data Index: 966662 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3505. Min Act: -0.0000

Data Index: 365331 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3847. Min Act: -0.0000

Data Index: 242447 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3444. Min Act: -0.0000

Data Index: 3050 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3789. Min Act: -0.0000

Data Index: 722557 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3789. Min Act: -0.0000

Data Index: 1003431 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3886. Min Act: -0.0000

Data Index: 555440 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.4280. Min Act: -0.0000

Data Index: 1271376 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.6226. Min Range: -1.6226

Max Act: 1.3579. Min Act: -0.0000

Data Index: 328717 (C4 (Web Text))

Max Activating Token Index: 573