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

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

Neuron 304 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.5172. Min Act: -0.0001

Data Index: 476172 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.5923. Min Act: -0.0001

Data Index: 448718 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.6626. Min Act: -0.0001

Data Index: 455438 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.6943. Min Act: -0.0001

Data Index: 830295 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.6493. Min Act: -0.0001

Data Index: 500132 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.6961. Min Act: -0.0001

Data Index: 364474 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.4707. Min Act: -0.0001

Data Index: 482527 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.6364. Min Act: -0.0001

Data Index: 351543 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.4813. Min Act: -0.0001

Data Index: 785087 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.4710. Min Act: -0.0001

Data Index: 475955 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.4364. Min Act: -0.0001

Data Index: 517381 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.5019. Min Act: -0.0001

Data Index: 1158819 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.3893. Min Act: -0.0001

Data Index: 585915 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.3105. Min Act: -0.0001

Data Index: 891009 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.1233. Min Act: -0.0001

Data Index: 989798 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.3706. Min Act: -0.0001

Data Index: 1153542 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.2968. Min Act: -0.0001

Data Index: 433766 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.2033. Min Act: -0.0001

Data Index: 1031521 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.2767. Min Act: -0.0001

Data Index: 232557 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 1.6961. Min Range: -1.6961

Max Act: 1.2813. Min Act: -0.0001

Data Index: 1245326 (C4 (Web Text))

Max Activating Token Index: 66