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

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

Neuron 2386 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3428. Min Act: -0.0001

Data Index: 853729 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3572. Min Act: -0.0001

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3358. Min Act: -0.0001

Data Index: 116525 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3483. Min Act: -0.0001

Data Index: 1643419 (Python Code)

Max Activating Token Index: 964

Text #4

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3263. Min Act: -0.0001

Data Index: 444340 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3351. Min Act: -0.0001

Data Index: 367696 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.3025. Min Act: -0.0001

Data Index: 666875 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2991. Min Act: -0.0001

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1060416 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2908. Min Act: -0.0001

Data Index: 1422728 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2893. Min Act: -0.0001

Data Index: 768648 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2984. Min Act: -0.0001

Data Index: 113323 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2956. Min Act: -0.0001

Data Index: 1245490 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2925. Min Act: -0.0001

Data Index: 1545101 (Python Code)

Max Activating Token Index: 775

Text #14

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2882. Min Act: -0.0001

Data Index: 482654 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2818. Min Act: -0.0001

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2839. Min Act: -0.0001

Data Index: 956562 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2798. Min Act: -0.0001

Data Index: 327754 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2778. Min Act: -0.0001

Data Index: 35684 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.3572. Min Range: -0.3572

Max Act: 0.2920. Min Act: -0.0001

Data Index: 590791 (C4 (Web Text))

Max Activating Token Index: 1012