Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1173 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.3265. Min Act: -0.0001

Data Index: 892285 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2993. Min Act: -0.0001

Data Index: 1010097 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2952. Min Act: -0.0001

Data Index: 821628 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2890. Min Act: -0.0001

Data Index: 213873 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2919. Min Act: -0.0001

Data Index: 984131 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2827. Min Act: -0.0001

Data Index: 919747 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2758. Min Act: -0.0001

Data Index: 152462 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2626. Min Act: -0.0001

Data Index: 911744 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1269408 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2744. Min Act: -0.0001

Data Index: 63440 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2675. Min Act: -0.0001

Data Index: 790876 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2546. Min Act: -0.0001

Data Index: 533429 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2524. Min Act: -0.0001

Data Index: 954088 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2613. Min Act: -0.0001

Data Index: 474050 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2594. Min Act: -0.0001

Data Index: 414223 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2596. Min Act: -0.0001

Data Index: 377725 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2552. Min Act: -0.0001

Data Index: 568038 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2526. Min Act: -0.0001

Data Index: 313754 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2521. Min Act: -0.0001

Data Index: 866927 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.3265. Min Range: -0.3265

Max Act: 0.2495. Min Act: -0.0001

Data Index: 878694 (C4 (Web Text))

Max Activating Token Index: 293