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

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

Neuron 4764 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1609711 (Python Code)

Max Activating Token Index: 149

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1337407 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0492. Min Act: -0.0001

Data Index: 587939 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1387104 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1373933 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1647626 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0473. Min Act: -0.0000

Data Index: 902830 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1615147 (Python Code)

Max Activating Token Index: 102

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0489. Min Act: -0.0000

Data Index: 860811 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1455666 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0477. Min Act: -0.0000

Data Index: 937680 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0444. Min Act: -0.0000

Data Index: 901116 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1141499 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0457. Min Act: -0.0000

Data Index: 1157264 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0454. Min Act: -0.0000

Data Index: 718456 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1399576 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1524787 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1491280 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1393719 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1402757 (Python Code)

Max Activating Token Index: 156