Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3061 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4129. Min Act: -0.0001

Data Index: 264434 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4447. Min Act: -0.0001

Data Index: 310669 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4612. Min Act: -0.0001

Data Index: 923941 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4042. Min Act: -0.0001

Data Index: 675739 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3900. Min Act: -0.0001

Data Index: 202877 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3654. Min Act: -0.0001

Data Index: 817291 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4141. Min Act: -0.0001

Data Index: 1072675 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3901. Min Act: -0.0001

Data Index: 1134960 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3861. Min Act: -0.0001

Data Index: 554709 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4335. Min Act: -0.0001

Data Index: 1044719 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3502. Min Act: -0.0001

Data Index: 39858 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4203. Min Act: -0.0001

Data Index: 637522 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3912. Min Act: -0.0001

Data Index: 929029 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4020. Min Act: -0.0001

Data Index: 1009002 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4008. Min Act: -0.0001

Data Index: 955823 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3875. Min Act: -0.0001

Data Index: 437464 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4175. Min Act: -0.0001

Data Index: 1296010 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3655. Min Act: -0.0001

Data Index: 1296327 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3497. Min Act: -0.0001

Data Index: 486015 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3564. Min Act: -0.0001

Data Index: 1313481 (C4 (Web Text))

Max Activating Token Index: 485