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

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

Neuron 1274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2652. Min Act: -0.0001

Data Index: 825919 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2597. Min Act: -0.0001

Data Index: 124617 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2770. Min Act: -0.0001

Data Index: 977150 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2626. Min Act: -0.0001

Data Index: 935107 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1211782 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2259. Min Act: -0.0001

Data Index: 167892 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2269. Min Act: -0.0001

Data Index: 1144444 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1234088 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2244. Min Act: -0.0001

Data Index: 660693 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2275. Min Act: -0.0001

Data Index: 943535 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1858. Min Act: -0.0001

Data Index: 802305 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2036. Min Act: -0.0001

Data Index: 848747 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2121. Min Act: -0.0001

Data Index: 683190 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2021. Min Act: -0.0001

Data Index: 155160 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1947. Min Act: -0.0001

Data Index: 252787 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1933. Min Act: -0.0001

Data Index: 575731 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2103. Min Act: -0.0001

Data Index: 524376 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1299258 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2001. Min Act: -0.0001

Data Index: 632864 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2097. Min Act: -0.0001

Data Index: 806952 (C4 (Web Text))

Max Activating Token Index: 490