Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3515 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3814. Min Act: -0.0000

Data Index: 767476 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1071056 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3644. Min Act: -0.0000

Data Index: 471252 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1236495 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1291944 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3383. Min Act: -0.0000

Data Index: 586948 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1141753 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3711. Min Act: -0.0000

Data Index: 295013 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3266. Min Act: -0.0000

Data Index: 555488 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3324. Min Act: -0.0000

Data Index: 280385 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1092790 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1068048 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1265228 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3104. Min Act: -0.0000

Data Index: 643582 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3170. Min Act: -0.0000

Data Index: 73301 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.3154. Min Act: -0.0000

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2962. Min Act: -0.0000

Data Index: 467138 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2894. Min Act: -0.0000

Data Index: 402966 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2881. Min Act: -0.0000

Data Index: 783305 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.3814. Min Range: -0.3814

Max Act: 0.2940. Min Act: -0.0000

Data Index: 741889 (C4 (Web Text))

Max Activating Token Index: 480