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

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

Neuron 3576 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: 2.3731. Min Range: -2.3731

Max Act: 2.3731. Min Act: -0.0000

Data Index: 1352787 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.3731. Min Range: -2.3731

Max Act: 2.1312. Min Act: -0.0000

Data Index: 1649522 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.9785. Min Act: -0.0000

Data Index: 965411 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.9582. Min Act: -0.0000

Data Index: 165611 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.7542. Min Act: -0.0000

Data Index: 1376370 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.7970. Min Act: -0.0000

Data Index: 1581282 (Python Code)

Max Activating Token Index: 928

Text #6

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.7605. Min Act: -0.0000

Data Index: 1284494 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1316748 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1386794 (Python Code)

Max Activating Token Index: 285

Text #9

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.5844. Min Act: -0.0000

Data Index: 814543 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1027343 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.5604. Min Act: -0.0000

Data Index: 247766 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.6315. Min Act: -0.0000

Data Index: 31259 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1511845 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.4281. Min Act: -0.0000

Data Index: 330451 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1580899 (Python Code)

Max Activating Token Index: 778

Text #16

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.4469. Min Act: -0.0000

Data Index: 902152 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.5715. Min Act: -0.0000

Data Index: 1586098 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.4546. Min Act: -0.0000

Data Index: 1357435 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 2.3731. Min Range: -2.3731

Max Act: 1.4480. Min Act: -0.0000

Data Index: 764360 (C4 (Web Text))

Max Activating Token Index: 525