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

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

Neuron 4415 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3313. Min Range: -4.3313

Max Act: 4.3313. Min Act: -0.0000

Data Index: 1457368 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 4.3313. Min Range: -4.3313

Max Act: 4.3056. Min Act: -0.0000

Data Index: 246064 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.7423. Min Act: -0.0000

Data Index: 78514 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.5907. Min Act: -0.0000

Data Index: 366893 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.6614. Min Act: -0.0000

Data Index: 367079 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.6336. Min Act: -0.0000

Data Index: 963256 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.7931. Min Act: -0.0000

Data Index: 1033114 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.6193. Min Act: -0.0000

Data Index: 230923 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.5707. Min Act: -0.0000

Data Index: 152985 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.5552. Min Act: -0.0000

Data Index: 1540498 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.4914. Min Act: -0.0000

Data Index: 700035 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.4893. Min Act: -0.0000

Data Index: 313216 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.3994. Min Act: -0.0000

Data Index: 157726 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.3830. Min Act: -0.0000

Data Index: 953110 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.3300. Min Act: -0.0000

Data Index: 1141194 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.1602. Min Act: -0.0000

Data Index: 856863 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.1710. Min Act: -0.0000

Data Index: 189630 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 4.3313. Min Range: -4.3313

Max Act: 2.9939. Min Act: -0.0000

Data Index: 334824 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 4.3313. Min Range: -4.3313

Max Act: 3.1747. Min Act: -0.0000

Data Index: 736936 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 4.3313. Min Range: -4.3313

Max Act: 2.9639. Min Act: -0.0000

Data Index: 172467 (C4 (Web Text))

Max Activating Token Index: 4