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

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

Neuron 1412 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: 3.2835. Min Range: -3.2835

Max Act: 3.1784. Min Act: -0.0000

Data Index: 1406726 (Python Code)

Max Activating Token Index: 839

Text #1

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0899. Min Act: -0.0000

Data Index: 1460881 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.7949. Min Act: -0.0000

Data Index: 1613269 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.2223. Min Act: -0.0000

Data Index: 1592123 (Python Code)

Max Activating Token Index: 366

Text #4

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.2835. Min Act: -0.0000

Data Index: 1390347 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.8039. Min Act: -0.0000

Data Index: 1376709 (Python Code)

Max Activating Token Index: 876

Text #6

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0597. Min Act: -0.0000

Data Index: 1459619 (Python Code)

Max Activating Token Index: 929

Text #7

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.7526. Min Act: -0.0000

Data Index: 1410353 (Python Code)

Max Activating Token Index: 893

Text #8

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.9444. Min Act: -0.0000

Data Index: 1560141 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.7593. Min Act: -0.0000

Data Index: 1638811 (Python Code)

Max Activating Token Index: 120

Text #10

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.7200. Min Act: -0.0000

Data Index: 1416259 (Python Code)

Max Activating Token Index: 905

Text #11

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.3114. Min Act: -0.0000

Data Index: 1501862 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.5512. Min Act: -0.0000

Data Index: 1383992 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.8191. Min Act: -0.0000

Data Index: 1417923 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1509497 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.8547. Min Act: -0.0000

Data Index: 1426731 (Python Code)

Max Activating Token Index: 698

Text #16

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.6021. Min Act: -0.0000

Data Index: 1428500 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.5843. Min Act: -0.0000

Data Index: 1393781 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.5675. Min Act: -0.0000

Data Index: 1525859 (Python Code)

Max Activating Token Index: 906

Text #19

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.7115. Min Act: -0.0000

Data Index: 1384773 (Python Code)

Max Activating Token Index: 770