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

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

Neuron 427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.7588. Min Act: -0.0003

Data Index: 1489991 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.7616. Min Act: -0.0003

Data Index: 1452143 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.7348. Min Act: -0.0003

Data Index: 1564941 (Python Code)

Max Activating Token Index: 897

Text #3

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6799. Min Act: -0.0003

Data Index: 1562592 (Python Code)

Max Activating Token Index: 526

Text #4

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5998. Min Act: -0.0003

Data Index: 1622378 (Python Code)

Max Activating Token Index: 276

Text #5

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6678. Min Act: -0.0003

Data Index: 1515386 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6739. Min Act: -0.0003

Data Index: 1573035 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5966. Min Act: -0.0003

Data Index: 1425440 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6179. Min Act: -0.0003

Data Index: 1535836 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6740. Min Act: -0.0003

Data Index: 1592060 (Python Code)

Max Activating Token Index: 883

Text #10

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6408. Min Act: -0.0003

Data Index: 1572743 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6542. Min Act: -0.0003

Data Index: 1427483 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6514. Min Act: -0.0003

Data Index: 1418953 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6811. Min Act: -0.0003

Data Index: 1404383 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6716. Min Act: -0.0003

Data Index: 1391342 (Python Code)

Max Activating Token Index: 947

Text #15

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6683. Min Act: -0.0003

Data Index: 1474251 (Python Code)

Max Activating Token Index: 159

Text #16

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6956. Min Act: -0.0003

Data Index: 1485459 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6482. Min Act: -0.0003

Data Index: 1366850 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6563. Min Act: -0.0003

Data Index: 1522909 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.7414. Min Act: -0.0003

Data Index: 1578237 (Python Code)

Max Activating Token Index: 688