Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4886 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1329729 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6723. Min Act: -0.0000

Data Index: 546073 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6167. Min Act: -0.0000

Data Index: 201168 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5192. Min Act: -0.0000

Data Index: 78282 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5323. Min Act: -0.0000

Data Index: 957205 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1055847 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5069. Min Act: -0.0000

Data Index: 409182 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4559. Min Act: 0.0001

Data Index: 1021424 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4740. Min Act: -0.0000

Data Index: 159847 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4607. Min Act: -0.0000

Data Index: 737911 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4730. Min Act: 0.0000

Data Index: 1104568 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1265733 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4883. Min Act: -0.0000

Data Index: 926292 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4533. Min Act: 0.0000

Data Index: 1240781 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1412117 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4476. Min Act: 0.0000

Data Index: 245974 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4438. Min Act: -0.0000

Data Index: 264681 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4452. Min Act: -0.0000

Data Index: 754113 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1592126 (Python Code)

Max Activating Token Index: 390

Text #19

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4540. Min Act: -0.0000

Data Index: 12147 (C4 (Web Text))

Max Activating Token Index: 194