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

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

Neuron 4880 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: 1.6159. Min Range: -1.6159

Max Act: 1.5328. Min Act: -0.0000

Data Index: 679897 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.6159. Min Act: -0.0000

Data Index: 36296 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.5763. Min Act: -0.0000

Data Index: 1418013 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.5299. Min Act: -0.0000

Data Index: 1283559 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.5277. Min Act: -0.0000

Data Index: 307656 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1584436 (Python Code)

Max Activating Token Index: 368

Text #6

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1625519 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1198246 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.3879. Min Act: -0.0000

Data Index: 504514 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.3680. Min Act: -0.0000

Data Index: 808921 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.3590. Min Act: -0.0000

Data Index: 999685 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1518721 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2261. Min Act: -0.0000

Data Index: 909908 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1964. Min Act: -0.0000

Data Index: 934675 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.3360. Min Act: -0.0000

Data Index: 706897 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1346836 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2200. Min Act: -0.0000

Data Index: 5647 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1156339 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.1471. Min Act: -0.0000

Data Index: 154724 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.6159. Min Range: -1.6159

Max Act: 1.2206. Min Act: -0.0000

Data Index: 801785 (C4 (Web Text))

Max Activating Token Index: 856