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

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

Neuron 1919 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: 2.0392. Min Range: -2.0392

Max Act: 2.0392. Min Act: -0.0000

Data Index: 1581224 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.7255. Min Act: -0.0000

Data Index: 195701 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.5208. Min Act: -0.0000

Data Index: 1432483 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1623643 (Python Code)

Max Activating Token Index: 993

Text #4

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.4487. Min Act: -0.0000

Data Index: 360941 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.5196. Min Act: -0.0000

Data Index: 528416 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.5218. Min Act: -0.0000

Data Index: 195124 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.4062. Min Act: -0.0000

Data Index: 408528 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1283362 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.4879. Min Act: -0.0000

Data Index: 676828 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1430983 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.3581. Min Act: -0.0000

Data Index: 927854 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.4503. Min Act: -0.0000

Data Index: 47139 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.3623. Min Act: -0.0000

Data Index: 63605 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.3699. Min Act: -0.0000

Data Index: 214642 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.2850. Min Act: -0.0000

Data Index: 717259 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.3512. Min Act: -0.0000

Data Index: 110974 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.2266. Min Act: -0.0000

Data Index: 276989 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.2545. Min Act: -0.0000

Data Index: 305689 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 2.0392. Min Range: -2.0392

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1007171 (C4 (Web Text))

Max Activating Token Index: 258