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

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

Neuron 2059 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2483. Min Range: -3.2483

Max Act: 3.2483. Min Act: -0.0000

Data Index: 1526040 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 3.2483. Min Range: -3.2483

Max Act: 3.0027. Min Act: -0.0000

Data Index: 1480071 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5133. Min Act: -0.0000

Data Index: 738925 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.6265. Min Act: -0.0000

Data Index: 1380372 (Python Code)

Max Activating Token Index: 267

Text #4

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5447. Min Act: -0.0000

Data Index: 434076 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.5331. Min Act: -0.0000

Data Index: 1608968 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.4757. Min Act: -0.0000

Data Index: 1416990 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.4438. Min Act: -0.0000

Data Index: 439844 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.2721. Min Act: -0.0000

Data Index: 1524124 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.2640. Min Act: -0.0000

Data Index: 31768 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 3.2483. Min Range: -3.2483

Max Act: 2.1641. Min Act: -0.0000

Data Index: 176909 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.9443. Min Act: -0.0000

Data Index: 1216594 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.9352. Min Act: -0.0000

Data Index: 985179 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.8530. Min Act: -0.0000

Data Index: 419398 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.8455. Min Act: -0.0000

Data Index: 1202481 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.7344. Min Act: -0.0000

Data Index: 337327 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.7183. Min Act: -0.0000

Data Index: 1357054 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.9059. Min Act: -0.0000

Data Index: 1253216 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.8062. Min Act: -0.0000

Data Index: 1061266 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 3.2483. Min Range: -3.2483

Max Act: 1.9019. Min Act: -0.0000

Data Index: 404755 (C4 (Web Text))

Max Activating Token Index: 607