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

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

Neuron 1140 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1089512 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1312658 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6535. Min Act: -0.0000

Data Index: 76067 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6486. Min Act: -0.0000

Data Index: 320956 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6494. Min Act: 0.0000

Data Index: 787711 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1165249 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5922. Min Act: -0.0000

Data Index: 516094 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.6148. Min Act: 0.0000

Data Index: 68007 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1027542 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5665. Min Act: -0.0000

Data Index: 429040 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5651. Min Act: -0.0000

Data Index: 299220 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5576. Min Act: -0.0000

Data Index: 371817 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5501. Min Act: -0.0000

Data Index: 730666 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5503. Min Act: -0.0000

Data Index: 559603 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5111. Min Act: -0.0000

Data Index: 939282 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5333. Min Act: -0.0000

Data Index: 976437 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5270. Min Act: -0.0000

Data Index: 917254 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.4973. Min Act: -0.0000

Data Index: 468604 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5252. Min Act: 0.0000

Data Index: 774562 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.7616. Min Range: -0.7616

Max Act: 0.5199. Min Act: -0.0000

Data Index: 314212 (C4 (Web Text))

Max Activating Token Index: 585