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

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

Neuron 5457 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4514. Min Act: -0.0000

Data Index: 952536 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.4346. Min Act: -0.0000

Data Index: 300328 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1213544 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3704. Min Act: -0.0000

Data Index: 571201 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3474. Min Act: -0.0000

Data Index: 321682 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3700. Min Act: -0.0000

Data Index: 131710 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3631. Min Act: -0.0000

Data Index: 84182 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3273. Min Act: -0.0000

Data Index: 932964 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3245. Min Act: -0.0000

Data Index: 519723 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1245405 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1292567 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1100567 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3379. Min Act: -0.0000

Data Index: 406028 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1006346 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3066. Min Act: -0.0000

Data Index: 520767 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.3028. Min Act: -0.0000

Data Index: 190085 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2893. Min Act: -0.0000

Data Index: 918459 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2954. Min Act: -0.0000

Data Index: 776714 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1081818 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.4514. Min Range: -0.4514

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1070054 (C4 (Web Text))

Max Activating Token Index: 12