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

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

Neuron 839 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6572. Min Act: -0.0000

Data Index: 490455 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5635. Min Act: -0.0000

Data Index: 312866 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5658. Min Act: -0.0000

Data Index: 902345 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5994. Min Act: -0.0000

Data Index: 411976 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5217. Min Act: 0.0000

Data Index: 472224 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1334880 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5065. Min Act: -0.0000

Data Index: 474102 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4588. Min Act: -0.0000

Data Index: 466272 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4790. Min Act: -0.0000

Data Index: 936087 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4792. Min Act: -0.0000

Data Index: 458221 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4747. Min Act: -0.0000

Data Index: 334560 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4672. Min Act: -0.0000

Data Index: 626660 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1035548 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4164. Min Act: -0.0000

Data Index: 100730 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4422. Min Act: -0.0000

Data Index: 472774 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4364. Min Act: -0.0000

Data Index: 149681 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1246415 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4374. Min Act: -0.0000

Data Index: 791348 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4337. Min Act: -0.0000

Data Index: 373643 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4049. Min Act: 0.0000

Data Index: 180975 (C4 (Web Text))

Max Activating Token Index: 215