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

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

Neuron 2026 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.9819. Min Act: -0.0001

Data Index: 488399 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8999. Min Act: -0.0001

Data Index: 571548 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1241275 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8939. Min Act: -0.0001

Data Index: 822667 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8408. Min Act: -0.0001

Data Index: 159243 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8102. Min Act: -0.0001

Data Index: 1128075 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8093. Min Act: -0.0001

Data Index: 555501 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7649. Min Act: -0.0001

Data Index: 791176 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8034. Min Act: -0.0001

Data Index: 757324 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7959. Min Act: -0.0001

Data Index: 65994 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1068164 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8429. Min Act: -0.0001

Data Index: 17456 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8169. Min Act: -0.0001

Data Index: 831327 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7625. Min Act: -0.0001

Data Index: 538106 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7054. Min Act: -0.0001

Data Index: 903996 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7906. Min Act: -0.0001

Data Index: 664264 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.8152. Min Act: -0.0001

Data Index: 1329811 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7591. Min Act: -0.0001

Data Index: 1200475 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7588. Min Act: -0.0001

Data Index: 349541 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.9819. Min Range: -0.9819

Max Act: 0.7544. Min Act: -0.0001

Data Index: 652555 (C4 (Web Text))

Max Activating Token Index: 206