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

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

Neuron 3022 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1283859 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1827. Min Act: -0.0000

Data Index: 700277 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1161406 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1735. Min Act: -0.0001

Data Index: 344555 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1707. Min Act: -0.0001

Data Index: 902558 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1286627 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1700. Min Act: -0.0001

Data Index: 913883 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1575. Min Act: -0.0000

Data Index: 803260 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1585. Min Act: -0.0001

Data Index: 219500 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1226923 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1646. Min Act: -0.0001

Data Index: 113751 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1509. Min Act: -0.0000

Data Index: 903143 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1543. Min Act: -0.0000

Data Index: 708951 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1348012 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1534. Min Act: -0.0001

Data Index: 865844 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1196644 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1469. Min Act: -0.0000

Data Index: 384259 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1562. Min Act: -0.0000

Data Index: 182393 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1271988 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.1970. Min Range: -0.1970

Max Act: 0.1500. Min Act: -0.0001

Data Index: 1110132 (C4 (Web Text))

Max Activating Token Index: 574