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

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

Neuron 3126 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: 1.0257. Min Range: -1.0257

Max Act: 1.0257. Min Act: -0.0000

Data Index: 274210 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9588. Min Act: -0.0001

Data Index: 399284 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7940. Min Act: -0.0001

Data Index: 385052 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8921. Min Act: -0.0001

Data Index: 9134 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8806. Min Act: -0.0001

Data Index: 159860 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8574. Min Act: -0.0001

Data Index: 191245 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8548. Min Act: -0.0001

Data Index: 295558 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.9703. Min Act: -0.0001

Data Index: 1224017 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8586. Min Act: -0.0001

Data Index: 99515 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7523. Min Act: -0.0001

Data Index: 440426 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7967. Min Act: -0.0000

Data Index: 905352 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7505. Min Act: -0.0001

Data Index: 664215 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8498. Min Act: -0.0001

Data Index: 316266 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7867. Min Act: -0.0001

Data Index: 681272 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8927. Min Act: -0.0001

Data Index: 855670 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1082938 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1276414 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7944. Min Act: -0.0001

Data Index: 272223 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.8033. Min Act: -0.0000

Data Index: 987349 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.0257. Min Range: -1.0257

Max Act: 0.7341. Min Act: -0.0000

Data Index: 430809 (C4 (Web Text))

Max Activating Token Index: 494