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

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

Neuron 1513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.9744. Min Act: -0.0001

Data Index: 601914 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.6628. Min Act: -0.0000

Data Index: 126600 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.6468. Min Act: -0.0000

Data Index: 796233 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.9461. Min Act: -0.0001

Data Index: 152717 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.9315. Min Act: -0.0000

Data Index: 1055825 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.1520. Min Act: -0.0000

Data Index: 251447 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.7463. Min Act: -0.0000

Data Index: 469423 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.5847. Min Act: -0.0000

Data Index: 697375 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.6975. Min Act: -0.0000

Data Index: 1143328 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.8889. Min Act: -0.0000

Data Index: 1087302 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.3679. Min Act: -0.0001

Data Index: 247917 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.0613. Min Act: -0.0000

Data Index: 151714 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.3165. Min Act: -0.0000

Data Index: 318615 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 4.0491. Min Range: -4.0491

Max Act: 4.0491. Min Act: -0.0000

Data Index: 1206354 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.5773. Min Act: -0.0000

Data Index: 1313122 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.5462. Min Act: -0.0000

Data Index: 259584 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.0624. Min Act: -0.0000

Data Index: 697803 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.4776. Min Act: -0.0000

Data Index: 274744 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.4948. Min Act: -0.0000

Data Index: 661212 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 4.0491. Min Range: -4.0491

Max Act: 3.4171. Min Act: -0.0001

Data Index: 754765 (C4 (Web Text))

Max Activating Token Index: 686