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

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

Neuron 2730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1322346 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8779. Min Act: -0.0000

Data Index: 410739 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8662. Min Act: -0.0000

Data Index: 727263 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1025930 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8352. Min Act: -0.0000

Data Index: 590150 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8150. Min Act: -0.0000

Data Index: 566044 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8146. Min Act: -0.0000

Data Index: 793172 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7391. Min Act: -0.0000

Data Index: 569866 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1129413 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6902. Min Act: -0.0000

Data Index: 925182 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7050. Min Act: -0.0000

Data Index: 990670 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7583. Min Act: -0.0000

Data Index: 62845 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7353. Min Act: -0.0000

Data Index: 382923 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7210. Min Act: -0.0000

Data Index: 323652 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6601. Min Act: -0.0000

Data Index: 581410 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6754. Min Act: -0.0000

Data Index: 205679 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6812. Min Act: -0.0000

Data Index: 641774 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6965. Min Act: -0.0000

Data Index: 340026 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6333. Min Act: -0.0000

Data Index: 193312 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1014850 (C4 (Web Text))

Max Activating Token Index: 177