Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3715 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1309. Min Range: -1.1309

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1086029 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 1.1309. Min Range: -1.1309

Max Act: 1.0577. Min Act: -0.0000

Data Index: 544048 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1074825 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.8783. Min Act: -0.0000

Data Index: 480191 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.8644. Min Act: -0.0000

Data Index: 184643 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1534932 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.8901. Min Act: -0.0000

Data Index: 818340 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7209. Min Act: -0.0000

Data Index: 348351 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7903. Min Act: -0.0000

Data Index: 397138 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7507. Min Act: -0.0000

Data Index: 899163 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1509938 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.8105. Min Act: -0.0000

Data Index: 410055 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7951. Min Act: -0.0000

Data Index: 209077 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.8097. Min Act: -0.0000

Data Index: 502 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1529018 (Python Code)

Max Activating Token Index: 610

Text #15

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1092289 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.6225. Min Act: -0.0000

Data Index: 1543370 (Python Code)

Max Activating Token Index: 166

Text #17

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.6756. Min Act: -0.0000

Data Index: 614313 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1285611 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 1.1309. Min Range: -1.1309

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1242397 (C4 (Web Text))

Max Activating Token Index: 260