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

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

Neuron 1940 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: 4.1895. Min Range: -4.1895

Max Act: 3.7630. Min Act: -0.0001

Data Index: 500475 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 4.1895. Min Range: -4.1895

Max Act: 4.1895. Min Act: -0.0000

Data Index: 1093996 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.6834. Min Act: -0.0001

Data Index: 1253715 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.4364. Min Act: -0.0000

Data Index: 1156336 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.4250. Min Act: -0.0000

Data Index: 1285555 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.6545. Min Act: -0.0001

Data Index: 396411 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.2141. Min Act: -0.0001

Data Index: 905092 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.7119. Min Act: -0.0001

Data Index: 280612 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.2536. Min Act: -0.0000

Data Index: 176676 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.3738. Min Act: -0.0000

Data Index: 653704 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.4654. Min Act: -0.0000

Data Index: 796056 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.6100. Min Act: -0.0001

Data Index: 530767 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.2654. Min Act: -0.0000

Data Index: 268461 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.5621. Min Act: -0.0001

Data Index: 387368 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.5559. Min Act: -0.0000

Data Index: 469037 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.4030. Min Act: -0.0000

Data Index: 1104817 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.2568. Min Act: -0.0001

Data Index: 1170870 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.4043. Min Act: -0.0000

Data Index: 653262 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.4011. Min Act: -0.0000

Data Index: 836546 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 4.1895. Min Range: -4.1895

Max Act: 3.3500. Min Act: -0.0001

Data Index: 187573 (C4 (Web Text))

Max Activating Token Index: 93