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

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

Neuron 3474 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.2136. Min Act: -0.0000

Data Index: 1027217 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.5418. Min Act: -0.0000

Data Index: 1073117 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.4646. Min Act: -0.0000

Data Index: 1235380 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 4.5418. Min Range: -4.5418

Max Act: 4.0547. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.4819. Min Act: -0.0000

Data Index: 839883 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.8045. Min Act: -0.0000

Data Index: 715805 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.5468. Min Act: -0.0000

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.8927. Min Act: -0.0000

Data Index: 913399 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.6947. Min Act: -0.0000

Data Index: 686893 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.6621. Min Act: -0.0000

Data Index: 80468 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.4767. Min Act: -0.0000

Data Index: 213115 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.7745. Min Act: -0.0000

Data Index: 265094 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.4449. Min Act: -0.0000

Data Index: 541930 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.7514. Min Act: -0.0000

Data Index: 76769 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.5454. Min Act: -0.0000

Data Index: 1051493 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.4947. Min Act: -0.0000

Data Index: 882771 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.6450. Min Act: -0.0000

Data Index: 541225 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.3040. Min Act: -0.0000

Data Index: 1262783 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.5862. Min Act: -0.0000

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 4.5418. Min Range: -4.5418

Max Act: 3.3993. Min Act: -0.0000

Data Index: 11185 (C4 (Web Text))

Max Activating Token Index: 752