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

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

Neuron 1324 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: 0.5970. Min Range: -0.5970

Max Act: 0.5970. Min Act: -0.0001

Data Index: 1252208 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1195140 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5777. Min Act: -0.0001

Data Index: 1594074 (Python Code)

Max Activating Token Index: 987

Text #3

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1650695 (Python Code)

Max Activating Token Index: 277

Text #4

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1342433 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5244. Min Act: -0.0000

Data Index: 91574 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5374. Min Act: -0.0001

Data Index: 1053870 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5186. Min Act: -0.0000

Data Index: 58362 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.5123. Min Act: -0.0000

Data Index: 716894 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1027949 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4826. Min Act: -0.0001

Data Index: 936199 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4774. Min Act: -0.0000

Data Index: 396407 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4724. Min Act: -0.0000

Data Index: 121 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4710. Min Act: -0.0000

Data Index: 591238 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4628. Min Act: -0.0000

Data Index: 573597 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4632. Min Act: -0.0000

Data Index: 474075 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1505275 (Python Code)

Max Activating Token Index: 610

Text #17

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4498. Min Act: -0.0001

Data Index: 1320605 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4466. Min Act: -0.0000

Data Index: 689698 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.5970. Min Range: -0.5970

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1434856 (Python Code)

Max Activating Token Index: 75