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

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

Neuron 4710 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: 2.2105. Min Range: -2.2105

Max Act: 1.7330. Min Act: -0.0000

Data Index: 451788 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.2105. Min Range: -2.2105

Max Act: 2.0077. Min Act: -0.0000

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.7663. Min Act: -0.0000

Data Index: 719790 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 2.2105. Min Range: -2.2105

Max Act: 2.2105. Min Act: -0.0000

Data Index: 638752 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.7825. Min Act: -0.0000

Data Index: 456499 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.6461. Min Act: -0.0000

Data Index: 807294 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1125174 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.7480. Min Act: -0.0000

Data Index: 335084 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.6352. Min Act: -0.0000

Data Index: 95610 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.6657. Min Act: -0.0000

Data Index: 690308 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.6091. Min Act: -0.0000

Data Index: 1148463 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.6601. Min Act: -0.0000

Data Index: 45762 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.3906. Min Act: -0.0000

Data Index: 1062585 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1270831 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.5024. Min Act: -0.0000

Data Index: 1267811 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.4542. Min Act: -0.0000

Data Index: 314260 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.3965. Min Act: -0.0000

Data Index: 282032 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1044851 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.4982. Min Act: -0.0000

Data Index: 716832 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 2.2105. Min Range: -2.2105

Max Act: 1.3811. Min Act: -0.0000

Data Index: 974168 (C4 (Web Text))

Max Activating Token Index: 715