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

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

Neuron 820 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4806. Min Act: -0.0001

Data Index: 284000 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4584. Min Act: -0.0001

Data Index: 31035 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3481. Min Act: -0.0001

Data Index: 262894 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4059. Min Act: -0.0001

Data Index: 1040855 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4243. Min Act: -0.0001

Data Index: 287183 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3720. Min Act: -0.0001

Data Index: 1098463 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3447. Min Act: -0.0001

Data Index: 1318130 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3767. Min Act: -0.0001

Data Index: 314139 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3815. Min Act: -0.0001

Data Index: 106121 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3646. Min Act: -0.0001

Data Index: 854094 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3920. Min Act: -0.0001

Data Index: 1106244 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3755. Min Act: -0.0001

Data Index: 1122632 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3880. Min Act: -0.0001

Data Index: 544283 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3656. Min Act: -0.0001

Data Index: 99259 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4066. Min Act: -0.0001

Data Index: 228711 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3471. Min Act: -0.0001

Data Index: 992373 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.4087. Min Act: -0.0001

Data Index: 1111441 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1028767 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3506. Min Act: -0.0001

Data Index: 814239 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.4806. Min Range: -0.4806

Max Act: 0.3584. Min Act: -0.0001

Data Index: 173132 (C4 (Web Text))

Max Activating Token Index: 484