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

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

Neuron 2179 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: 1.8563. Min Range: -1.8563

Max Act: 1.8563. Min Act: -0.0001

Data Index: 1571477 (Python Code)

Max Activating Token Index: 133

Text #1

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.7019. Min Act: -0.0001

Data Index: 1557329 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6296. Min Act: -0.0001

Data Index: 1559044 (Python Code)

Max Activating Token Index: 887

Text #3

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.7489. Min Act: -0.0001

Data Index: 1517200 (Python Code)

Max Activating Token Index: 382

Text #4

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5593. Min Act: -0.0001

Data Index: 1466351 (Python Code)

Max Activating Token Index: 808

Text #5

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6581. Min Act: -0.0001

Data Index: 1438579 (Python Code)

Max Activating Token Index: 808

Text #6

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5651. Min Act: -0.0001

Data Index: 1480457 (Python Code)

Max Activating Token Index: 838

Text #7

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1532369 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5978. Min Act: -0.0001

Data Index: 1517379 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1537331 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.6051. Min Act: -0.0000

Data Index: 1385300 (Python Code)

Max Activating Token Index: 741

Text #11

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.3908. Min Act: -0.0001

Data Index: 1593277 (Python Code)

Max Activating Token Index: 71

Text #12

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4285. Min Act: -0.0001

Data Index: 1407351 (Python Code)

Max Activating Token Index: 853

Text #13

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.5249. Min Act: -0.0001

Data Index: 1637234 (Python Code)

Max Activating Token Index: 615

Text #14

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.3749. Min Act: -0.0001

Data Index: 1490898 (Python Code)

Max Activating Token Index: 226

Text #15

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4428. Min Act: -0.0001

Data Index: 1430150 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.2936. Min Act: -0.0001

Data Index: 1639715 (Python Code)

Max Activating Token Index: 790

Text #17

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.3368. Min Act: -0.0001

Data Index: 1562325 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1396859 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 1.8563. Min Range: -1.8563

Max Act: 1.4024. Min Act: -0.0001

Data Index: 1643801 (Python Code)

Max Activating Token Index: 32