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

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

Neuron 572 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: 0.8438. Min Range: -0.8438

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1223939 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1057188 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1040725 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7096. Min Act: -0.0000

Data Index: 655017 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7596. Min Act: -0.0000

Data Index: 47362 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6878. Min Act: -0.0000

Data Index: 771362 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7081. Min Act: -0.0000

Data Index: 972534 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7559. Min Act: -0.0000

Data Index: 284549 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6904. Min Act: -0.0000

Data Index: 316942 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6469. Min Act: -0.0000

Data Index: 212074 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1116520 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1046584 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5814. Min Act: -0.0000

Data Index: 984489 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6363. Min Act: -0.0000

Data Index: 344890 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6790. Min Act: -0.0000

Data Index: 629578 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6382. Min Act: -0.0000

Data Index: 58507 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6203. Min Act: -0.0000

Data Index: 511974 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6154. Min Act: -0.0000

Data Index: 575204 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6115. Min Act: -0.0000

Data Index: 809013 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6287. Min Act: -0.0000

Data Index: 240380 (C4 (Web Text))

Max Activating Token Index: 42