Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 800 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.7694. Min Act: -0.0001

Data Index: 1083275 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6744. Min Act: -0.0000

Data Index: 51264 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.6210. Min Act: -0.0000

Data Index: 216988 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5109. Min Act: -0.0000

Data Index: 291437 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5716. Min Act: -0.0000

Data Index: 756576 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5371. Min Act: -0.0000

Data Index: 161388 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5086. Min Act: -0.0000

Data Index: 440485 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4574. Min Act: -0.0000

Data Index: 601234 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1105472 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4328. Min Act: -0.0001

Data Index: 689483 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5502. Min Act: -0.0001

Data Index: 1059053 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1093535 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4484. Min Act: -0.0000

Data Index: 313962 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1291596 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5120. Min Act: -0.0000

Data Index: 650716 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5398. Min Act: -0.0001

Data Index: 964155 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.5133. Min Act: -0.0000

Data Index: 541056 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4405. Min Act: -0.0001

Data Index: 746711 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1148702 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.7694. Min Range: -0.7694

Max Act: 0.4863. Min Act: -0.0001

Data Index: 847247 (C4 (Web Text))

Max Activating Token Index: 646