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

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

Neuron 3793 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: 2.1489. Min Range: -2.1489

Max Act: 2.1489. Min Act: -0.0000

Data Index: 783270 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 2.1489. Min Range: -2.1489

Max Act: 2.0976. Min Act: -0.0000

Data Index: 987985 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 2.1489. Min Range: -2.1489

Max Act: 2.0494. Min Act: -0.0000

Data Index: 456660 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.8857. Min Act: -0.0000

Data Index: 704484 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.8591. Min Act: -0.0000

Data Index: 662804 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.8590. Min Act: -0.0000

Data Index: 38436 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.7984. Min Act: -0.0000

Data Index: 678891 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.6731. Min Act: -0.0000

Data Index: 1171047 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.6750. Min Act: -0.0000

Data Index: 762300 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.6768. Min Act: -0.0000

Data Index: 635513 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.5629. Min Act: -0.0000

Data Index: 76603 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.5560. Min Act: -0.0000

Data Index: 892272 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1246903 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.6450. Min Act: -0.0000

Data Index: 308587 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.6073. Min Act: -0.0000

Data Index: 56631 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.5563. Min Act: -0.0000

Data Index: 867425 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.6434. Min Act: -0.0000

Data Index: 343147 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.5464. Min Act: -0.0000

Data Index: 998131 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1342037 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 2.1489. Min Range: -2.1489

Max Act: 1.4520. Min Act: -0.0000

Data Index: 1273155 (C4 (Web Text))

Max Activating Token Index: 209