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

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

Neuron 488 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1057. Min Range: -1.1057

Max Act: 1.1057. Min Act: -0.0000

Data Index: 800903 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1209920 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8807. Min Act: -0.0000

Data Index: 219318 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1354408 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8018. Min Act: -0.0000

Data Index: 82154 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8543. Min Act: -0.0000

Data Index: 99001 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7571. Min Act: -0.0000

Data Index: 231241 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8011. Min Act: -0.0000

Data Index: 199355 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7542. Min Act: -0.0000

Data Index: 249292 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7440. Min Act: -0.0000

Data Index: 701735 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7113. Min Act: -0.0000

Data Index: 983054 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7081. Min Act: -0.0000

Data Index: 211739 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1185016 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.7559. Min Act: -0.0000

Data Index: 413325 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6431. Min Act: -0.0000

Data Index: 541892 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6891. Min Act: -0.0000

Data Index: 985524 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6422. Min Act: -0.0000

Data Index: 426707 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6842. Min Act: -0.0000

Data Index: 870077 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1236441 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1141755 (C4 (Web Text))

Max Activating Token Index: 567