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

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

Neuron 5127 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0593. Min Range: -1.0593

Max Act: 1.0593. Min Act: -0.0000

Data Index: 853286 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.9523. Min Act: -0.0000

Data Index: 334223 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1272159 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1324553 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.9300. Min Act: -0.0000

Data Index: 352492 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8935. Min Act: -0.0000

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8375. Min Act: -0.0000

Data Index: 59153 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8487. Min Act: 0.0000

Data Index: 1389994 (Python Code)

Max Activating Token Index: 648

Text #8

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8623. Min Act: -0.0000

Data Index: 615365 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8336. Min Act: -0.0000

Data Index: 824801 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8231. Min Act: -0.0000

Data Index: 16523 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8423. Min Act: -0.0000

Data Index: 756945 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7716. Min Act: 0.0000

Data Index: 694457 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.9215. Min Act: -0.0000

Data Index: 819538 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8716. Min Act: -0.0000

Data Index: 222645 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7851. Min Act: -0.0000

Data Index: 239474 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.8143. Min Act: -0.0000

Data Index: 815740 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7883. Min Act: -0.0000

Data Index: 291180 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7282. Min Act: -0.0000

Data Index: 485562 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.0593. Min Range: -1.0593

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1114950 (C4 (Web Text))

Max Activating Token Index: 885