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

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

Neuron 2640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.8187. Min Act: -0.0001

Data Index: 1493038 (Python Code)

Max Activating Token Index: 589

Text #1

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.9042. Min Act: -0.0000

Data Index: 1629545 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.9348. Min Act: -0.0000

Data Index: 1550463 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7928. Min Act: -0.0000

Data Index: 1528175 (Python Code)

Max Activating Token Index: 559

Text #4

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.8696. Min Act: -0.0000

Data Index: 1532980 (Python Code)

Max Activating Token Index: 906

Text #5

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1553747 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1421763 (Python Code)

Max Activating Token Index: 236

Text #7

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1601059 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5581. Min Act: -0.0000

Data Index: 1440091 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.6403. Min Act: -0.0000

Data Index: 1389578 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.6830. Min Act: -0.0000

Data Index: 1438322 (Python Code)

Max Activating Token Index: 851

Text #11

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1541710 (Python Code)

Max Activating Token Index: 194

Text #12

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.4997. Min Act: -0.0000

Data Index: 1407166 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5307. Min Act: -0.0000

Data Index: 1534915 (Python Code)

Max Activating Token Index: 647

Text #14

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1574915 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1374178 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5902. Min Act: -0.0001

Data Index: 1368737 (Python Code)

Max Activating Token Index: 566

Text #17

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5477. Min Act: -0.0000

Data Index: 1461291 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.4985. Min Act: -0.0000

Data Index: 1589701 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 1.9348. Min Range: -1.9348

Max Act: 1.5869. Min Act: -0.0000

Data Index: 1621178 (Python Code)

Max Activating Token Index: 597