Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1339 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0006

Data Index: 352680 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0645. Min Act: -0.0006

Data Index: 107804 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0620. Min Act: -0.0006

Data Index: 954833 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0620. Min Act: -0.0006

Data Index: 592186 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0588. Min Act: -0.0006

Data Index: 809067 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0605. Min Act: -0.0006

Data Index: 97357 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0623. Min Act: -0.0006

Data Index: 832130 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0596. Min Act: -0.0006

Data Index: 1110886 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0585. Min Act: -0.0006

Data Index: 648130 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0554. Min Act: -0.0006

Data Index: 207081 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0543. Min Act: -0.0006

Data Index: 1080387 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0536. Min Act: -0.0006

Data Index: 1327875 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0556. Min Act: -0.0006

Data Index: 641219 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0505. Min Act: -0.0006

Data Index: 934224 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0545. Min Act: -0.0006

Data Index: 873417 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0541. Min Act: -0.0006

Data Index: 1005039 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0563. Min Act: -0.0006

Data Index: 1149302 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0530. Min Act: -0.0006

Data Index: 600724 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0532. Min Act: -0.0006

Data Index: 777293 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1276815 (C4 (Web Text))

Max Activating Token Index: 144