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

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

Neuron 2978 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: 1.7749. Min Range: -1.7749

Max Act: 1.7386. Min Act: -0.0001

Data Index: 590971 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7749. Min Act: -0.0001

Data Index: 9969 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7080. Min Act: -0.0001

Data Index: 274857 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7020. Min Act: -0.0001

Data Index: 180542 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.6900. Min Act: -0.0001

Data Index: 550848 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7270. Min Act: -0.0001

Data Index: 895595 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7740. Min Act: -0.0001

Data Index: 191847 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7501. Min Act: -0.0001

Data Index: 763918 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.6599. Min Act: -0.0001

Data Index: 1355478 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.7664. Min Act: -0.0001

Data Index: 1354940 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.6803. Min Act: -0.0001

Data Index: 813051 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.6674. Min Act: -0.0001

Data Index: 560892 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.6432. Min Act: -0.0001

Data Index: 1088351 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.4321. Min Act: -0.0001

Data Index: 625298 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.6444. Min Act: -0.0001

Data Index: 827954 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.5721. Min Act: -0.0001

Data Index: 327381 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.5739. Min Act: -0.0001

Data Index: 997213 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.5365. Min Act: -0.0001

Data Index: 643510 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.4262. Min Act: -0.0001

Data Index: 270312 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.7749. Min Range: -1.7749

Max Act: 1.4724. Min Act: -0.0001

Data Index: 391875 (C4 (Web Text))

Max Activating Token Index: 560