Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1388 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4480. Min Act: -0.0001

Data Index: 1406763 (Python Code)

Max Activating Token Index: 329

Text #1

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4712. Min Act: -0.0000

Data Index: 541945 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4508. Min Act: -0.0001

Data Index: 1055412 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4775. Min Act: -0.0001

Data Index: 173327 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4158. Min Act: -0.0001

Data Index: 1413071 (Python Code)

Max Activating Token Index: 430

Text #5

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1534426 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4191. Min Act: -0.0001

Data Index: 1545337 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4195. Min Act: -0.0000

Data Index: 889859 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4052. Min Act: -0.0001

Data Index: 918639 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3795. Min Act: -0.0001

Data Index: 1004315 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3947. Min Act: -0.0000

Data Index: 820746 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1237541 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.4006. Min Act: -0.0001

Data Index: 1517650 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3509. Min Act: -0.0001

Data Index: 647037 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1478470 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1108483 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3594. Min Act: -0.0000

Data Index: 509955 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3740. Min Act: -0.0001

Data Index: 1555143 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3592. Min Act: -0.0001

Data Index: 931838 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.4775. Min Range: -0.4775

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1401127 (Python Code)

Max Activating Token Index: 754