Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 514 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2984. Min Range: -5.2984

Max Act: 5.2984. Min Act: -0.0000

Data Index: 625923 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 5.2984. Min Range: -5.2984

Max Act: 4.4364. Min Act: -0.0000

Data Index: 865273 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 5.2984. Min Range: -5.2984

Max Act: 4.4560. Min Act: -0.0000

Data Index: 1060474 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 5.2984. Min Range: -5.2984

Max Act: 4.4378. Min Act: -0.0000

Data Index: 871365 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 5.2984. Min Range: -5.2984

Max Act: 4.2324. Min Act: -0.0000

Data Index: 79774 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 5.2984. Min Range: -5.2984

Max Act: 4.0574. Min Act: -0.0000

Data Index: 853704 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.7885. Min Act: -0.0000

Data Index: 727201 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.7381. Min Act: -0.0000

Data Index: 203804 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.6757. Min Act: -0.0000

Data Index: 1302361 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.9409. Min Act: -0.0000

Data Index: 517764 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.7609. Min Act: -0.0000

Data Index: 717256 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.6994. Min Act: -0.0000

Data Index: 233154 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.6922. Min Act: -0.0000

Data Index: 1281192 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.6487. Min Act: -0.0000

Data Index: 566735 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.6144. Min Act: -0.0000

Data Index: 436031 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.6160. Min Act: -0.0000

Data Index: 607057 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.7596. Min Act: -0.0000

Data Index: 663736 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.5785. Min Act: -0.0000

Data Index: 1109910 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.7466. Min Act: -0.0000

Data Index: 74922 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 5.2984. Min Range: -5.2984

Max Act: 3.7294. Min Act: -0.0000

Data Index: 747635 (C4 (Web Text))

Max Activating Token Index: 570