Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2342 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.7168. Min Act: -0.0000

Data Index: 166523 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.4809. Min Act: -0.0000

Data Index: 1225098 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.7168. Min Range: -1.7168

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1147123 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.9449. Min Act: -0.0000

Data Index: 589171 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8656. Min Act: -0.0000

Data Index: 471785 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8720. Min Act: -0.0000

Data Index: 414034 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8657. Min Act: -0.0000

Data Index: 994308 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8261. Min Act: -0.0000

Data Index: 226354 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8399. Min Act: -0.0000

Data Index: 453032 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1130342 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1329304 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8006. Min Act: -0.0000

Data Index: 298257 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8061. Min Act: -0.0000

Data Index: 746389 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.8153. Min Act: -0.0000

Data Index: 284692 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.7935. Min Act: -0.0000

Data Index: 386827 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1168460 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.7785. Min Act: -0.0000

Data Index: 307749 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.7889. Min Act: -0.0000

Data Index: 159448 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.7554. Min Act: -0.0000

Data Index: 137452 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.7168. Min Range: -1.7168

Max Act: 0.7010. Min Act: 0.0000

Data Index: 371915 (C4 (Web Text))

Max Activating Token Index: 77