Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6018 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2592. Min Act: -0.0000

Data Index: 729721 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2347. Min Act: -0.0000

Data Index: 21885 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2091. Min Act: -0.0000

Data Index: 950761 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1978. Min Act: -0.0000

Data Index: 944418 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1859. Min Act: -0.0000

Data Index: 138176 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1856. Min Act: -0.0000

Data Index: 674971 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1915. Min Act: -0.0000

Data Index: 988797 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1945. Min Act: -0.0000

Data Index: 341387 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1130072 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1238741 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1701. Min Act: -0.0000

Data Index: 439195 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1137287 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1616924 (Python Code)

Max Activating Token Index: 184

Text #13

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1633. Min Act: -0.0000

Data Index: 924088 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1565. Min Act: -0.0000

Data Index: 19978 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1476. Min Act: -0.0000

Data Index: 586888 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1574. Min Act: -0.0000

Data Index: 246239 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1560. Min Act: -0.0000

Data Index: 252602 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1020079 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.1439. Min Act: -0.0000

Data Index: 815287 (C4 (Web Text))

Max Activating Token Index: 477