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

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

Neuron 3212 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.6786. Min Act: -0.0001

Data Index: 102876 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.6853. Min Act: -0.0001

Data Index: 744526 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.5988. Min Act: -0.0001

Data Index: 1331007 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.5980. Min Act: -0.0001

Data Index: 392038 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.5050. Min Act: -0.0002

Data Index: 82869 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4540. Min Act: -0.0001

Data Index: 615680 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.5161. Min Act: -0.0001

Data Index: 1309782 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.5040. Min Act: -0.0002

Data Index: 1185580 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4793. Min Act: -0.0001

Data Index: 1078825 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4687. Min Act: -0.0002

Data Index: 212161 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.5120. Min Act: -0.0001

Data Index: 769 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1337307 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4571. Min Act: -0.0001

Data Index: 372682 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.5183. Min Act: -0.0001

Data Index: 1274904 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4855. Min Act: -0.0001

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4621. Min Act: -0.0001

Data Index: 883716 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4793. Min Act: -0.0001

Data Index: 853027 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4403. Min Act: -0.0001

Data Index: 271074 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4777. Min Act: -0.0002

Data Index: 311501 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.6853. Min Range: -0.6853

Max Act: 0.4594. Min Act: -0.0001

Data Index: 1384390 (Python Code)

Max Activating Token Index: 161