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

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

Neuron 3911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0167. Min Range: -3.0167

Max Act: 3.0167. Min Act: -0.0000

Data Index: 458712 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.7078. Min Act: -0.0000

Data Index: 982963 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.4202. Min Act: -0.0000

Data Index: 216578 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.2796. Min Act: -0.0000

Data Index: 1333449 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.3118. Min Act: -0.0000

Data Index: 149166 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.1713. Min Act: -0.0000

Data Index: 215684 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.0876. Min Act: -0.0000

Data Index: 1234782 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.1886. Min Act: -0.0000

Data Index: 30672 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.9356. Min Act: -0.0000

Data Index: 1113327 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.8975. Min Act: -0.0000

Data Index: 42969 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.9862. Min Act: -0.0000

Data Index: 572381 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.8889. Min Act: -0.0000

Data Index: 300314 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.9819. Min Act: -0.0000

Data Index: 733450 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.8691. Min Act: -0.0000

Data Index: 1137436 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.0759. Min Act: -0.0000

Data Index: 975049 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.0474. Min Act: -0.0000

Data Index: 201423 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.9231. Min Act: -0.0000

Data Index: 93034 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 3.0167. Min Range: -3.0167

Max Act: 2.0172. Min Act: -0.0000

Data Index: 1161659 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.8862. Min Act: -0.0000

Data Index: 74482 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 3.0167. Min Range: -3.0167

Max Act: 1.8763. Min Act: -0.0000

Data Index: 539060 (C4 (Web Text))

Max Activating Token Index: 465