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

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

Neuron 1464 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1067621 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3739. Min Act: -0.0000

Data Index: 120069 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3503. Min Act: -0.0000

Data Index: 432356 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3589. Min Act: -0.0000

Data Index: 47862 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3564. Min Act: -0.0000

Data Index: 303026 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1163116 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3405. Min Act: -0.0000

Data Index: 836302 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3283. Min Act: -0.0000

Data Index: 525237 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1386047 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3205. Min Act: -0.0000

Data Index: 638512 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1259064 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1434229 (Python Code)

Max Activating Token Index: 429

Text #12

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2947. Min Act: -0.0000

Data Index: 837105 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2973. Min Act: -0.0000

Data Index: 248727 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3087. Min Act: -0.0000

Data Index: 578021 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1508757 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1040043 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2996. Min Act: -0.0000

Data Index: 734057 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1038151 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1547808 (Python Code)

Max Activating Token Index: 600