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

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

Neuron 5248 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6359. Min Range: -4.6359

Max Act: 4.5891. Min Act: -0.0000

Data Index: 1127653 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 4.6359. Min Range: -4.6359

Max Act: 4.6359. Min Act: -0.0000

Data Index: 270372 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 4.6359. Min Range: -4.6359

Max Act: 4.3958. Min Act: -0.0000

Data Index: 181158 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 4.6359. Min Range: -4.6359

Max Act: 4.0301. Min Act: -0.0000

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 4.6359. Min Range: -4.6359

Max Act: 4.0987. Min Act: -0.0000

Data Index: 539455 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.9052. Min Act: -0.0000

Data Index: 483317 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.8614. Min Act: -0.0000

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 4.6359. Min Range: -4.6359

Max Act: 4.0483. Min Act: -0.0000

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.5698. Min Act: -0.0000

Data Index: 272460 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.6962. Min Act: -0.0000

Data Index: 1024230 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.7012. Min Act: -0.0000

Data Index: 619003 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.6539. Min Act: -0.0000

Data Index: 1130363 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.5082. Min Act: -0.0000

Data Index: 370353 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.5172. Min Act: -0.0000

Data Index: 916616 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.3888. Min Act: -0.0000

Data Index: 1129069 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.6749. Min Act: -0.0000

Data Index: 708894 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.3793. Min Act: -0.0000

Data Index: 258983 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.5002. Min Act: -0.0000

Data Index: 307655 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.4913. Min Act: -0.0000

Data Index: 994640 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 4.6359. Min Range: -4.6359

Max Act: 3.2399. Min Act: -0.0000

Data Index: 832304 (C4 (Web Text))

Max Activating Token Index: 763