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

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

Neuron 4710 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3051. Min Range: -3.3051

Max Act: 3.1364. Min Act: -0.0000

Data Index: 552044 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 3.3051. Min Range: -3.3051

Max Act: 3.2393. Min Act: -0.0000

Data Index: 733449 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 3.3051. Min Range: -3.3051

Max Act: 3.2075. Min Act: -0.0000

Data Index: 834292 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 3.3051. Min Range: -3.3051

Max Act: 3.3051. Min Act: -0.0000

Data Index: 1122798 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 3.3051. Min Range: -3.3051

Max Act: 3.1078. Min Act: -0.0000

Data Index: 776328 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.9100. Min Act: -0.0000

Data Index: 738429 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 3.3051. Min Range: -3.3051

Max Act: 3.1871. Min Act: -0.0000

Data Index: 422958 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.9924. Min Act: -0.0000

Data Index: 1462861 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.9410. Min Act: -0.0000

Data Index: 70380 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.7985. Min Act: -0.0000

Data Index: 174712 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 3.3051. Min Range: -3.3051

Max Act: 3.0340. Min Act: -0.0000

Data Index: 2835 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.8436. Min Act: -0.0000

Data Index: 1577922 (Python Code)

Max Activating Token Index: 711

Text #12

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.7261. Min Act: -0.0000

Data Index: 13933 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.5821. Min Act: -0.0000

Data Index: 898493 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.7049. Min Act: -0.0000

Data Index: 399593 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.5710. Min Act: -0.0000

Data Index: 480868 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.8113. Min Act: -0.0000

Data Index: 772497 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.6706. Min Act: -0.0000

Data Index: 723007 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.6263. Min Act: -0.0000

Data Index: 481791 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 3.3051. Min Range: -3.3051

Max Act: 2.3688. Min Act: -0.0000

Data Index: 665215 (C4 (Web Text))

Max Activating Token Index: 879