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

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

Neuron 1406 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: 3.3000. Min Range: -3.3000

Max Act: 3.3000. Min Act: -0.0000

Data Index: 735894 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 3.3000. Min Range: -3.3000

Max Act: 3.1346. Min Act: -0.0000

Data Index: 179238 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.5874. Min Act: -0.0000

Data Index: 750101 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.5685. Min Act: -0.0000

Data Index: 383411 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.4369. Min Act: -0.0000

Data Index: 476610 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.6535. Min Act: -0.0000

Data Index: 1132344 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.3367. Min Act: -0.0001

Data Index: 1043627 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.5634. Min Act: -0.0000

Data Index: 728115 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.2205. Min Act: -0.0000

Data Index: 300314 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.9841. Min Act: -0.0000

Data Index: 277923 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0376. Min Act: -0.0000

Data Index: 143109 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0034. Min Act: -0.0001

Data Index: 361531 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.1505. Min Act: -0.0000

Data Index: 899104 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.9847. Min Act: -0.0000

Data Index: 837748 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0895. Min Act: -0.0000

Data Index: 734171 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.1170. Min Act: -0.0000

Data Index: 223995 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.7632. Min Act: -0.0000

Data Index: 678788 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.9598. Min Act: -0.0000

Data Index: 599122 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 3.3000. Min Range: -3.3000

Max Act: 1.9072. Min Act: -0.0000

Data Index: 897103 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.3000. Min Range: -3.3000

Max Act: 2.0276. Min Act: -0.0000

Data Index: 726043 (C4 (Web Text))

Max Activating Token Index: 273