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

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

Neuron 1678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.4135. Min Act: -0.0000

Data Index: 529065 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.0506. Min Act: -0.0000

Data Index: 1619090 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.1973. Min Act: -0.0000

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 3.4163. Min Range: -3.4163

Max Act: 3.4163. Min Act: -0.0000

Data Index: 1642034 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.6739. Min Act: -0.0000

Data Index: 137547 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.7344. Min Act: -0.0000

Data Index: 923494 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.4068. Min Act: 0.0001

Data Index: 1503027 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5800. Min Act: -0.0000

Data Index: 886665 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2412. Min Act: 0.0000

Data Index: 493812 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5993. Min Act: -0.0000

Data Index: 1354118 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.5136. Min Act: -0.0000

Data Index: 1495086 (Python Code)

Max Activating Token Index: 550

Text #11

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2535. Min Act: 0.0000

Data Index: 1431717 (Python Code)

Max Activating Token Index: 680

Text #12

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2089. Min Act: -0.0000

Data Index: 802928 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3321. Min Act: -0.0000

Data Index: 886134 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.4644. Min Act: -0.0000

Data Index: 1221800 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.3173. Min Act: -0.0000

Data Index: 1538706 (Python Code)

Max Activating Token Index: 422

Text #16

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.2573. Min Act: -0.0000

Data Index: 298260 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.1225. Min Act: -0.0000

Data Index: 1548199 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 3.4163. Min Range: -3.4163

Max Act: 2.1802. Min Act: 0.0001

Data Index: 1640210 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 3.4163. Min Range: -3.4163

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1526902 (Python Code)

Max Activating Token Index: 727