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

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

Neuron 6043 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4470. Min Range: -5.4470

Max Act: 5.4470. Min Act: -0.0000

Data Index: 35174 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 5.4470. Min Range: -5.4470

Max Act: 4.7878. Min Act: -0.0000

Data Index: 255783 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 5.4470. Min Range: -5.4470

Max Act: 3.7799. Min Act: -0.0000

Data Index: 760368 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 5.4470. Min Range: -5.4470

Max Act: 3.8078. Min Act: -0.0000

Data Index: 611713 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 5.4470. Min Range: -5.4470

Max Act: 3.2826. Min Act: -0.0000

Data Index: 282790 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 5.4470. Min Range: -5.4470

Max Act: 3.4105. Min Act: -0.0000

Data Index: 375080 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.6596. Min Act: -0.0000

Data Index: 870779 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.4710. Min Act: -0.0000

Data Index: 648159 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.9929. Min Act: -0.0000

Data Index: 308982 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.4549. Min Act: -0.0000

Data Index: 410308 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.6900. Min Act: -0.0000

Data Index: 521797 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.3078. Min Act: -0.0000

Data Index: 960351 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.3482. Min Act: -0.0000

Data Index: 259283 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 5.4470. Min Range: -5.4470

Max Act: 1.8518. Min Act: -0.0000

Data Index: 527954 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.2994. Min Act: -0.0000

Data Index: 421390 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.2782. Min Act: -0.0000

Data Index: 350167 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.1173. Min Act: -0.0000

Data Index: 552200 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.1682. Min Act: -0.0000

Data Index: 1101070 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.2196. Min Act: -0.0000

Data Index: 52984 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 5.4470. Min Range: -5.4470

Max Act: 2.1856. Min Act: -0.0000

Data Index: 648643 (C4 (Web Text))

Max Activating Token Index: 310