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

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

Neuron 5900 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.9022. Min Act: -0.0000

Data Index: 152818 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1382902 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.9296. Min Act: -0.0001

Data Index: 1582616 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1171854 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.8397. Min Act: -0.0001

Data Index: 1626659 (Python Code)

Max Activating Token Index: 581

Text #5

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.8180. Min Act: -0.0001

Data Index: 1360860 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7971. Min Act: -0.0000

Data Index: 172512 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7644. Min Act: -0.0001

Data Index: 818524 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.8649. Min Act: -0.0001

Data Index: 644612 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7374. Min Act: -0.0001

Data Index: 1289811 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1482926 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7896. Min Act: -0.0001

Data Index: 1380283 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7745. Min Act: -0.0001

Data Index: 1561136 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7976. Min Act: -0.0000

Data Index: 141637 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7063. Min Act: -0.0001

Data Index: 1514440 (Python Code)

Max Activating Token Index: 539

Text #15

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.6850. Min Act: -0.0001

Data Index: 1566972 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1649970 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.6830. Min Act: -0.0001

Data Index: 142052 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1367854 (Python Code)

Max Activating Token Index: 473

Text #19

Max Range: 0.9296. Min Range: -0.9296

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1595994 (Python Code)

Max Activating Token Index: 363