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

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

Neuron 3678 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: 1.8949. Min Range: -1.8949

Max Act: 1.8949. Min Act: -0.0000

Data Index: 1464804 (Python Code)

Max Activating Token Index: 207

Text #1

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.6156. Min Act: -0.0001

Data Index: 1570024 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.5899. Min Act: -0.0001

Data Index: 979272 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.3835. Min Act: -0.0001

Data Index: 1646940 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.2933. Min Act: -0.0000

Data Index: 398700 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.3008. Min Act: -0.0001

Data Index: 1543317 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.2933. Min Act: -0.0001

Data Index: 1520685 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1422105 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1245. Min Act: -0.0001

Data Index: 389045 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.2391. Min Act: -0.0001

Data Index: 1408034 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1680. Min Act: -0.0001

Data Index: 222619 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.2409. Min Act: -0.0000

Data Index: 887929 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1607893 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1949. Min Act: -0.0000

Data Index: 561763 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1104165 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1725. Min Act: -0.0001

Data Index: 780341 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1174. Min Act: -0.0001

Data Index: 1627240 (Python Code)

Max Activating Token Index: 491

Text #17

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1560644 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.0801. Min Act: -0.0000

Data Index: 416975 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 1.8949. Min Range: -1.8949

Max Act: 1.1919. Min Act: -0.0000

Data Index: 1308184 (C4 (Web Text))

Max Activating Token Index: 1017