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

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

Neuron 1693 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2311. Min Range: -2.2311

Max Act: 2.2311. Min Act: -0.0000

Data Index: 1068643 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 2.2311. Min Range: -2.2311

Max Act: 2.0472. Min Act: -0.0001

Data Index: 845177 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.9136. Min Act: -0.0000

Data Index: 760975 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 2.2311. Min Range: -2.2311

Max Act: 2.0510. Min Act: -0.0000

Data Index: 1359036 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.7808. Min Act: -0.0000

Data Index: 1131128 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.7733. Min Act: -0.0001

Data Index: 1096597 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6928. Min Act: -0.0000

Data Index: 138508 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6823. Min Act: -0.0001

Data Index: 1018769 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6316. Min Act: -0.0001

Data Index: 279009 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6173. Min Act: -0.0000

Data Index: 478857 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.5337. Min Act: -0.0001

Data Index: 847032 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6626. Min Act: -0.0000

Data Index: 425146 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.5683. Min Act: -0.0000

Data Index: 365746 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1052741 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6355. Min Act: -0.0000

Data Index: 1018811 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.7311. Min Act: -0.0000

Data Index: 419207 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6988. Min Act: -0.0000

Data Index: 488130 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.5312. Min Act: -0.0000

Data Index: 151390 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.6780. Min Act: -0.0001

Data Index: 1161348 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 2.2311. Min Range: -2.2311

Max Act: 1.5974. Min Act: -0.0001

Data Index: 947250 (C4 (Web Text))

Max Activating Token Index: 547