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

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

Neuron 857 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: 0.1616. Min Range: -0.1616

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1262958 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1584. Min Act: -0.0001

Data Index: 300327 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1582. Min Act: -0.0001

Data Index: 709621 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1590. Min Act: -0.0001

Data Index: 615970 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1121412 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1564. Min Act: -0.0001

Data Index: 489071 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1549. Min Act: -0.0001

Data Index: 286096 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1591. Min Act: -0.0001

Data Index: 556770 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1602. Min Act: -0.0001

Data Index: 910891 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1145399 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1107688 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1502. Min Act: -0.0001

Data Index: 123844 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1524. Min Act: -0.0001

Data Index: 473300 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1503. Min Act: -0.0001

Data Index: 71852 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1576. Min Act: -0.0001

Data Index: 84873 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1536. Min Act: -0.0001

Data Index: 935543 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1491. Min Act: -0.0001

Data Index: 272939 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1554. Min Act: -0.0001

Data Index: 327495 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1462. Min Act: -0.0001

Data Index: 188107 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1468. Min Act: -0.0001

Data Index: 967500 (C4 (Web Text))

Max Activating Token Index: 504