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

Dataset: The Pile

Neuron 4406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.6472. Min Act: -0.0000

Data Index: 389475 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1075750 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5713. Min Act: -0.0000

Data Index: 811870 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5522. Min Act: -0.0000

Data Index: 873297 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1287410 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1050541 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1080359 (The Pile)

Max Activating Token Index: 232

Text #7

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1621464 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1502401 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1228427 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1889078 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1883877 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1388819 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4996. Min Act: -0.0000

Data Index: 879446 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4824. Min Act: -0.0000

Data Index: 988439 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1766027 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1766616 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1178347 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1364142 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.6472. Min Range: -0.6472

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1074813 (The Pile)

Max Activating Token Index: 968