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

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

Neuron 4186 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.7557. Min Act: -0.0001

Data Index: 269279 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 4.1529. Min Range: -4.1529

Max Act: 4.0683. Min Act: -0.0001

Data Index: 1130102 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 4.1529. Min Range: -4.1529

Max Act: 4.1529. Min Act: -0.0001

Data Index: 62110 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 4.1529. Min Range: -4.1529

Max Act: 4.0719. Min Act: -0.0000

Data Index: 1158994 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.6913. Min Act: -0.0001

Data Index: 262176 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.5327. Min Act: -0.0001

Data Index: 1202927 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.5771. Min Act: -0.0001

Data Index: 790145 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.6857. Min Act: -0.0001

Data Index: 870569 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.5151. Min Act: -0.0000

Data Index: 516819 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.8064. Min Act: -0.0001

Data Index: 1013041 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.4740. Min Act: -0.0000

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.5295. Min Act: -0.0001

Data Index: 392381 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.4509. Min Act: -0.0000

Data Index: 769350 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.3761. Min Act: -0.0001

Data Index: 306518 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.0830. Min Act: -0.0000

Data Index: 1311349 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.1713. Min Act: -0.0001

Data Index: 782178 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.3310. Min Act: -0.0000

Data Index: 187259 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.4982. Min Act: -0.0000

Data Index: 964939 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.4011. Min Act: -0.0001

Data Index: 1241657 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 4.1529. Min Range: -4.1529

Max Act: 3.0768. Min Act: -0.0001

Data Index: 1163701 (C4 (Web Text))

Max Activating Token Index: 958