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

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

Neuron 487 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0561. Min Range: -3.0561

Max Act: 3.0561. Min Act: -0.0000

Data Index: 1321162 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 3.0561. Min Range: -3.0561

Max Act: 3.0314. Min Act: -0.0000

Data Index: 201684 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 3.0561. Min Range: -3.0561

Max Act: 3.0305. Min Act: -0.0000

Data Index: 1082625 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.7867. Min Act: -0.0000

Data Index: 310481 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.8853. Min Act: -0.0000

Data Index: 689774 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.8807. Min Act: -0.0000

Data Index: 559141 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.8603. Min Act: -0.0000

Data Index: 474739 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1028829 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.7946. Min Act: -0.0000

Data Index: 12213 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.7830. Min Act: -0.0000

Data Index: 191960 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.7339. Min Act: -0.0000

Data Index: 847569 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.7305. Min Act: -0.0000

Data Index: 529269 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.7164. Min Act: -0.0000

Data Index: 1123012 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.6004. Min Act: -0.0000

Data Index: 1056233 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.6845. Min Act: -0.0000

Data Index: 1514001 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.7804. Min Act: -0.0000

Data Index: 1257433 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.6323. Min Act: -0.0000

Data Index: 814350 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.6082. Min Act: -0.0000

Data Index: 1469870 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.6098. Min Act: -0.0000

Data Index: 1105683 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 3.0561. Min Range: -3.0561

Max Act: 2.4658. Min Act: -0.0000

Data Index: 133505 (C4 (Web Text))

Max Activating Token Index: 359