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

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

Neuron 3058 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: 0.5451. Min Range: -0.5451

Max Act: 0.5431. Min Act: -0.0001

Data Index: 41861 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5451. Min Act: -0.0001

Data Index: 423798 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5195. Min Act: -0.0001

Data Index: 756798 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5157. Min Act: -0.0001

Data Index: 1025712 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4909. Min Act: -0.0001

Data Index: 796938 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4880. Min Act: -0.0001

Data Index: 758666 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4879. Min Act: -0.0001

Data Index: 1283786 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4380. Min Act: -0.0001

Data Index: 1146841 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4643. Min Act: -0.0001

Data Index: 1314129 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4360. Min Act: -0.0001

Data Index: 876161 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4411. Min Act: -0.0001

Data Index: 1289237 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4422. Min Act: -0.0001

Data Index: 849995 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4138. Min Act: -0.0001

Data Index: 281083 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4573. Min Act: -0.0001

Data Index: 108971 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4098. Min Act: -0.0001

Data Index: 235953 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3841. Min Act: -0.0001

Data Index: 394551 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4220. Min Act: -0.0001

Data Index: 559491 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4049. Min Act: -0.0001

Data Index: 391426 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3988. Min Act: -0.0001

Data Index: 792481 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4153. Min Act: -0.0001

Data Index: 92175 (C4 (Web Text))

Max Activating Token Index: 970