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

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

Neuron 294 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: 3.4992. Min Range: -3.4992

Max Act: 3.4992. Min Act: -0.0000

Data Index: 199690 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.8742. Min Act: -0.0001

Data Index: 1380056 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.9711. Min Act: -0.0000

Data Index: 1370968 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.9565. Min Act: -0.0001

Data Index: 1607842 (Python Code)

Max Activating Token Index: 137

Text #4

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.7758. Min Act: -0.0001

Data Index: 1412111 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.9077. Min Act: -0.0001

Data Index: 1628791 (Python Code)

Max Activating Token Index: 638

Text #6

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.7596. Min Act: -0.0001

Data Index: 1455459 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.6946. Min Act: -0.0001

Data Index: 1605522 (Python Code)

Max Activating Token Index: 628

Text #8

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.6592. Min Act: -0.0001

Data Index: 1388084 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.7305. Min Act: -0.0001

Data Index: 1583155 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.8560. Min Act: -0.0001

Data Index: 1630184 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.7140. Min Act: -0.0001

Data Index: 69378 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.8291. Min Act: -0.0001

Data Index: 1576209 (Python Code)

Max Activating Token Index: 596

Text #13

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.6614. Min Act: -0.0000

Data Index: 283831 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.5986. Min Act: -0.0001

Data Index: 1434300 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.4598. Min Act: -0.0001

Data Index: 1387927 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.3615. Min Act: -0.0001

Data Index: 493320 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.5251. Min Act: -0.0001

Data Index: 1593366 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.6553. Min Act: -0.0001

Data Index: 1600343 (Python Code)

Max Activating Token Index: 481

Text #19

Max Range: 3.4992. Min Range: -3.4992

Max Act: 2.3934. Min Act: -0.0001

Data Index: 1520048 (Python Code)

Max Activating Token Index: 725