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

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

Neuron 2246 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4705. Min Range: -5.4705

Max Act: 5.4705. Min Act: -0.0001

Data Index: 308033 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 5.4705. Min Range: -5.4705

Max Act: 5.1582. Min Act: -0.0001

Data Index: 187254 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.5685. Min Act: -0.0001

Data Index: 796985 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.5518. Min Act: -0.0001

Data Index: 533543 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.4410. Min Act: -0.0001

Data Index: 191186 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.4302. Min Act: -0.0001

Data Index: 1331453 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.2592. Min Act: -0.0001

Data Index: 431194 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.3864. Min Act: -0.0001

Data Index: 160419 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.3416. Min Act: -0.0001

Data Index: 127226 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.1476. Min Act: -0.0001

Data Index: 1243696 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.1148. Min Act: -0.0001

Data Index: 850166 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.2781. Min Act: -0.0001

Data Index: 1005754 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.0771. Min Act: -0.0001

Data Index: 836358 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.2257. Min Act: -0.0001

Data Index: 643720 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.0882. Min Act: -0.0001

Data Index: 150631 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 5.4705. Min Range: -5.4705

Max Act: 3.9317. Min Act: -0.0001

Data Index: 760038 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.0567. Min Act: -0.0001

Data Index: 77834 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.0352. Min Act: -0.0001

Data Index: 98944 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 5.4705. Min Range: -5.4705

Max Act: 4.0335. Min Act: -0.0001

Data Index: 289809 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 5.4705. Min Range: -5.4705

Max Act: 3.8234. Min Act: -0.0001

Data Index: 522895 (C4 (Web Text))

Max Activating Token Index: 728