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

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

Neuron 5763 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0256. Min Act: -0.0000

Data Index: 1320696 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.9741. Min Act: -0.0000

Data Index: 897776 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 2.0864. Min Range: -2.0864

Max Act: 2.0864. Min Act: -0.0000

Data Index: 1149172 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.9703. Min Act: -0.0000

Data Index: 888584 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.8618. Min Act: -0.0000

Data Index: 1639599 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.8931. Min Act: -0.0000

Data Index: 1498606 (Python Code)

Max Activating Token Index: 68

Text #6

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1410878 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.8138. Min Act: -0.0000

Data Index: 608603 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.7961. Min Act: -0.0000

Data Index: 833257 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1212346 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.8311. Min Act: -0.0000

Data Index: 1383442 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.8198. Min Act: -0.0000

Data Index: 1411269 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.6939. Min Act: -0.0000

Data Index: 1400219 (Python Code)

Max Activating Token Index: 596

Text #13

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.8740. Min Act: -0.0000

Data Index: 825509 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.6639. Min Act: -0.0000

Data Index: 1488290 (Python Code)

Max Activating Token Index: 112

Text #15

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.6716. Min Act: -0.0000

Data Index: 819610 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.7007. Min Act: -0.0000

Data Index: 1606132 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.6576. Min Act: -0.0000

Data Index: 651079 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1585028 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 2.0864. Min Range: -2.0864

Max Act: 1.6893. Min Act: -0.0000

Data Index: 1420664 (Python Code)

Max Activating Token Index: 475