Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0651. Min Range: -3.0651

Max Act: 3.0651. Min Act: -0.0001

Data Index: 861799 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.9554. Min Act: -0.0001

Data Index: 835943 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.6510. Min Act: -0.0001

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.8452. Min Act: -0.0001

Data Index: 1214127 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.5774. Min Act: -0.0001

Data Index: 981049 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.4667. Min Act: -0.0001

Data Index: 964184 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.4660. Min Act: -0.0001

Data Index: 828483 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.5768. Min Act: -0.0001

Data Index: 911970 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.6751. Min Act: -0.0001

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.5213. Min Act: -0.0001

Data Index: 558223 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.6584. Min Act: -0.0001

Data Index: 561511 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.5361. Min Act: -0.0001

Data Index: 495461 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.1046. Min Act: -0.0001

Data Index: 317524 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.2623. Min Act: -0.0001

Data Index: 1221634 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.3278. Min Act: -0.0001

Data Index: 1340616 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.5472. Min Act: -0.0001

Data Index: 575546 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.5262. Min Act: -0.0001

Data Index: 931273 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.3914. Min Act: -0.0001

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.3414. Min Act: -0.0002

Data Index: 706502 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 3.0651. Min Range: -3.0651

Max Act: 2.4535. Min Act: -0.0001

Data Index: 184363 (C4 (Web Text))

Max Activating Token Index: 719