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

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

Neuron 907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8879. Min Act: -0.0000

Data Index: 702679 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8743. Min Act: -0.0000

Data Index: 669394 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7865. Min Act: -0.0000

Data Index: 251288 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8091. Min Act: -0.0000

Data Index: 662223 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8758. Min Act: -0.0000

Data Index: 642201 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8249. Min Act: -0.0000

Data Index: 271731 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8380. Min Act: -0.0001

Data Index: 92888 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1328468 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7681. Min Act: -0.0000

Data Index: 339402 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6955. Min Act: -0.0000

Data Index: 734936 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7387. Min Act: -0.0000

Data Index: 224194 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.8140. Min Act: -0.0000

Data Index: 55312 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7345. Min Act: -0.0000

Data Index: 435907 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1348471 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1112272 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1284653 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6621. Min Act: -0.0000

Data Index: 853342 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6954. Min Act: -0.0000

Data Index: 571512 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6220. Min Act: -0.0000

Data Index: 847744 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.8879. Min Range: -0.8879

Max Act: 0.6838. Min Act: -0.0000

Data Index: 560906 (C4 (Web Text))

Max Activating Token Index: 879