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

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

Neuron 4263 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: 1.3535. Min Range: -1.3535

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1361651 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 1.3535. Min Range: -1.3535

Max Act: 1.2791. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.3535. Min Range: -1.3535

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1636226 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 1.3535. Min Range: -1.3535

Max Act: 1.0816. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1439059 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 1.3535. Min Range: -1.3535

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1457323 (Python Code)

Max Activating Token Index: 678

Text #7

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9510. Min Act: -0.0000

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1365630 (Python Code)

Max Activating Token Index: 667

Text #9

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1414447 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1538701 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1458046 (Python Code)

Max Activating Token Index: 187

Text #12

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1365053 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1470831 (Python Code)

Max Activating Token Index: 776

Text #14

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.8842. Min Act: -0.0000

Data Index: 70816 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1448644 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1378938 (Python Code)

Max Activating Token Index: 713

Text #17

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 1.3535. Min Range: -1.3535

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1368406 (Python Code)

Max Activating Token Index: 758