Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4053 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5575. Min Range: -2.5575

Max Act: 2.5575. Min Act: -0.0000

Data Index: 592255 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 2.5575. Min Range: -2.5575

Max Act: 2.1804. Min Act: -0.0000

Data Index: 1098793 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.5575. Min Range: -2.5575

Max Act: 2.0343. Min Act: -0.0000

Data Index: 255383 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.5575. Min Range: -2.5575

Max Act: 2.1354. Min Act: -0.0000

Data Index: 782776 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.9636. Min Act: -0.0000

Data Index: 240355 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.7306. Min Act: -0.0000

Data Index: 49826 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1270148 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4501. Min Act: -0.0000

Data Index: 481775 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4250. Min Act: -0.0000

Data Index: 335997 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1301165 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4103. Min Act: -0.0000

Data Index: 799991 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.3205. Min Act: -0.0000

Data Index: 595518 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1008156 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4668. Min Act: -0.0000

Data Index: 163265 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.3849. Min Act: -0.0000

Data Index: 996155 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1083710 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.2894. Min Act: -0.0000

Data Index: 921585 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1153404 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.3235. Min Act: -0.0000

Data Index: 318901 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 2.5575. Min Range: -2.5575

Max Act: 1.2972. Min Act: -0.0000

Data Index: 520116 (C4 (Web Text))

Max Activating Token Index: 345