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

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

Neuron 3741 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.4646. Min Act: -0.0001

Data Index: 698048 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.3294. Min Act: -0.0001

Data Index: 285599 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.1840. Min Act: -0.0001

Data Index: 233403 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0955. Min Act: -0.0001

Data Index: 1075835 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.1396. Min Act: -0.0001

Data Index: 98984 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0491. Min Act: -0.0001

Data Index: 313053 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9676. Min Act: -0.0001

Data Index: 689381 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0421. Min Act: -0.0001

Data Index: 657863 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0990. Min Act: -0.0001

Data Index: 1348147 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0091. Min Act: -0.0001

Data Index: 488380 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9498. Min Act: -0.0001

Data Index: 469291 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0723. Min Act: -0.0001

Data Index: 710960 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9399. Min Act: -0.0001

Data Index: 967425 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0430. Min Act: -0.0001

Data Index: 190407 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0142. Min Act: -0.0001

Data Index: 1201138 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9757. Min Act: -0.0001

Data Index: 1198913 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9635. Min Act: -0.0001

Data Index: 8138 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9560. Min Act: -0.0001

Data Index: 157088 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 1.4646. Min Range: -1.4646

Max Act: 1.0592. Min Act: -0.0001

Data Index: 66025 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.4646. Min Range: -1.4646

Max Act: 0.9725. Min Act: -0.0001

Data Index: 1168296 (C4 (Web Text))

Max Activating Token Index: 204