Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1561 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1456634 (Python Code)

Max Activating Token Index: 457

Text #1

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1734. Min Act: -0.0001

Data Index: 1651752 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0862. Min Act: -0.0001

Data Index: 1393599 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0899. Min Act: -0.0001

Data Index: 1459178 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0747. Min Act: -0.0001

Data Index: 1601756 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0351. Min Act: -0.0001

Data Index: 1627782 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0499. Min Act: -0.0001

Data Index: 1576190 (Python Code)

Max Activating Token Index: 861

Text #7

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1507790 (Python Code)

Max Activating Token Index: 442

Text #8

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.8638. Min Act: -0.0001

Data Index: 1531840 (Python Code)

Max Activating Token Index: 840

Text #9

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.9978. Min Act: -0.0001

Data Index: 1626811 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0922. Min Act: -0.0001

Data Index: 1591331 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0042. Min Act: -0.0001

Data Index: 1606126 (Python Code)

Max Activating Token Index: 672

Text #12

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.9424. Min Act: -0.0001

Data Index: 1378181 (Python Code)

Max Activating Token Index: 935

Text #13

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.9210. Min Act: -0.0001

Data Index: 1581375 (Python Code)

Max Activating Token Index: 383

Text #14

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.9460. Min Act: -0.0001

Data Index: 1428370 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.9574. Min Act: -0.0001

Data Index: 1523216 (Python Code)

Max Activating Token Index: 926

Text #16

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.8489. Min Act: -0.0001

Data Index: 487028 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.8988. Min Act: -0.0001

Data Index: 1475758 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1590202 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 1.3203. Min Range: -1.3203

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1484805 (Python Code)

Max Activating Token Index: 989