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

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

Neuron 1675 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6416. Min Act: -0.0000

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5446. Min Act: -0.0000

Data Index: 862144 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5470. Min Act: -0.0000

Data Index: 19991 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5298. Min Act: -0.0000

Data Index: 182537 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5078. Min Act: -0.0000

Data Index: 184319 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1071524 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4973. Min Act: -0.0000

Data Index: 37119 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4777. Min Act: -0.0000

Data Index: 437987 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4884. Min Act: -0.0000

Data Index: 872254 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4855. Min Act: -0.0000

Data Index: 934593 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4791. Min Act: -0.0000

Data Index: 521872 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1624795 (Python Code)

Max Activating Token Index: 502

Text #12

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1219551 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4599. Min Act: -0.0000

Data Index: 506093 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4841. Min Act: -0.0000

Data Index: 730157 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1287191 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1275674 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4656. Min Act: -0.0000

Data Index: 660494 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4673. Min Act: -0.0000

Data Index: 805813 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1212088 (C4 (Web Text))

Max Activating Token Index: 395