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

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

Neuron 3285 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.6164. Min Act: -0.0000

Data Index: 87768 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.5435. Min Act: -0.0000

Data Index: 171110 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4917. Min Act: -0.0000

Data Index: 977389 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1127196 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4657. Min Act: -0.0000

Data Index: 902117 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4515. Min Act: -0.0000

Data Index: 567135 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4587. Min Act: -0.0000

Data Index: 879965 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4127. Min Act: -0.0000

Data Index: 408011 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4466. Min Act: -0.0000

Data Index: 634270 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4120. Min Act: -0.0000

Data Index: 967351 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4262. Min Act: -0.0000

Data Index: 317387 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4022. Min Act: -0.0000

Data Index: 977209 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4021. Min Act: -0.0000

Data Index: 331228 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1255319 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3946. Min Act: -0.0000

Data Index: 610165 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3901. Min Act: -0.0000

Data Index: 469360 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3890. Min Act: -0.0000

Data Index: 672432 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.4262. Min Act: -0.0000

Data Index: 454123 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1128540 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.6164. Min Range: -0.6164

Max Act: 0.3509. Min Act: -0.0000

Data Index: 873037 (C4 (Web Text))

Max Activating Token Index: 518