Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3945 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.3290. Min Act: -0.0000

Data Index: 659306 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9915. Min Act: -0.0000

Data Index: 20606 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8517. Min Act: -0.0000

Data Index: 56884 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.3290. Min Range: -1.3290

Max Act: 1.0751. Min Act: -0.0000

Data Index: 534798 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1138447 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1167784 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8716. Min Act: -0.0000

Data Index: 42114 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9207. Min Act: -0.0000

Data Index: 93362 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9329. Min Act: -0.0000

Data Index: 863536 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8692. Min Act: -0.0000

Data Index: 20935 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.9077. Min Act: -0.0000

Data Index: 998793 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8863. Min Act: -0.0000

Data Index: 495695 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8574. Min Act: -0.0000

Data Index: 679351 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8786. Min Act: -0.0000

Data Index: 970257 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8216. Min Act: -0.0000

Data Index: 399913 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8440. Min Act: -0.0000

Data Index: 133985 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1336186 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.8299. Min Act: -0.0000

Data Index: 1141349 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1187880 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 1.3290. Min Range: -1.3290

Max Act: 0.7925. Min Act: -0.0000

Data Index: 74908 (C4 (Web Text))

Max Activating Token Index: 333