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

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

Neuron 10 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: 0.8786. Min Range: -0.8786

Max Act: 0.8786. Min Act: -0.0001

Data Index: 1329145 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.7742. Min Act: -0.0001

Data Index: 280633 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.7393. Min Act: -0.0001

Data Index: 311657 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.7437. Min Act: -0.0001

Data Index: 568959 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.5765. Min Act: -0.0001

Data Index: 3389 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.7090. Min Act: -0.0001

Data Index: 74964 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.7290. Min Act: -0.0001

Data Index: 911153 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6811. Min Act: -0.0001

Data Index: 356950 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6547. Min Act: -0.0001

Data Index: 46991 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6785. Min Act: -0.0001

Data Index: 1323672 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1159355 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6532. Min Act: -0.0001

Data Index: 422513 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6756. Min Act: -0.0001

Data Index: 581248 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6674. Min Act: -0.0001

Data Index: 127492 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6916. Min Act: -0.0001

Data Index: 672442 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6522. Min Act: -0.0001

Data Index: 981754 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6257. Min Act: -0.0001

Data Index: 134983 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6936. Min Act: -0.0001

Data Index: 516895 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6620. Min Act: -0.0001

Data Index: 160802 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.8786. Min Range: -0.8786

Max Act: 0.6890. Min Act: -0.0001

Data Index: 436358 (C4 (Web Text))

Max Activating Token Index: 719