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

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

Neuron 4696 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: 1.3699. Min Range: -1.3699

Max Act: 1.3699. Min Act: -0.0000

Data Index: 859533 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.0692. Min Act: -0.0000

Data Index: 537748 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.3699. Min Range: -1.3699

Max Act: 1.0109. Min Act: -0.0000

Data Index: 424689 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.9669. Min Act: -0.0000

Data Index: 542264 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1172319 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8660. Min Act: -0.0000

Data Index: 354926 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.9420. Min Act: -0.0000

Data Index: 10634 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1326211 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8921. Min Act: -0.0000

Data Index: 322731 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1102068 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8938. Min Act: -0.0000

Data Index: 769340 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1029892 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8553. Min Act: -0.0000

Data Index: 334732 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8094. Min Act: -0.0000

Data Index: 658658 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1173502 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1287299 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.7550. Min Act: -0.0000

Data Index: 619990 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8257. Min Act: -0.0000

Data Index: 215046 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.8014. Min Act: -0.0000

Data Index: 984987 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.3699. Min Range: -1.3699

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1301870 (C4 (Web Text))

Max Activating Token Index: 672