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

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

Neuron 3367 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6630. Min Act: -0.0000

Data Index: 510928 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6666. Min Act: -0.0000

Data Index: 848931 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6289. Min Act: -0.0000

Data Index: 140439 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5900. Min Act: -0.0000

Data Index: 103387 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6176. Min Act: -0.0000

Data Index: 399955 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5879. Min Act: -0.0000

Data Index: 384355 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1335343 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4533. Min Act: -0.0000

Data Index: 904943 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4325. Min Act: -0.0000

Data Index: 115819 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4161. Min Act: -0.0000

Data Index: 200885 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1079197 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3682. Min Act: -0.0000

Data Index: 644431 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3446. Min Act: -0.0000

Data Index: 538461 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3502. Min Act: -0.0000

Data Index: 656518 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3544. Min Act: -0.0000

Data Index: 852877 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3226. Min Act: -0.0000

Data Index: 201762 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3351. Min Act: -0.0000

Data Index: 624564 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1224606 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3530. Min Act: -0.0000

Data Index: 698206 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3410. Min Act: -0.0000

Data Index: 245857 (C4 (Web Text))

Max Activating Token Index: 564