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

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

Neuron 5235 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.3869. Min Act: -0.0000

Data Index: 93582 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.4184. Min Act: 0.0000

Data Index: 493791 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.9676. Min Act: -0.0000

Data Index: 567611 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.0497. Min Act: -0.0000

Data Index: 334619 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8969. Min Act: -0.0000

Data Index: 1004659 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.9976. Min Act: -0.0000

Data Index: 604802 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8967. Min Act: -0.0000

Data Index: 1280586 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8940. Min Act: 0.0000

Data Index: 128161 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8337. Min Act: -0.0000

Data Index: 93106 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7839. Min Act: -0.0000

Data Index: 188160 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7749. Min Act: -0.0000

Data Index: 643542 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7618. Min Act: -0.0000

Data Index: 127818 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8864. Min Act: -0.0000

Data Index: 613733 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8598. Min Act: -0.0000

Data Index: 182586 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.6608. Min Act: -0.0000

Data Index: 1248994 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7453. Min Act: -0.0000

Data Index: 73419 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7281. Min Act: -0.0000

Data Index: 214246 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.6138. Min Act: -0.0000

Data Index: 640430 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7853. Min Act: -0.0000

Data Index: 500628 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1274156 (C4 (Web Text))

Max Activating Token Index: 399