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

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

Neuron 3003 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: 2.8166. Min Range: -2.8166

Max Act: 2.5643. Min Act: -0.0000

Data Index: 600671 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.8166. Min Act: -0.0000

Data Index: 560410 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.3930. Min Act: -0.0000

Data Index: 310157 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.9564. Min Act: -0.0000

Data Index: 352722 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.0527. Min Act: -0.0000

Data Index: 687992 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.8166. Min Range: -2.8166

Max Act: 2.0326. Min Act: -0.0000

Data Index: 853889 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.9961. Min Act: -0.0000

Data Index: 746640 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8734. Min Act: -0.0000

Data Index: 893647 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8649. Min Act: -0.0000

Data Index: 1197127 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8440. Min Act: -0.0000

Data Index: 835223 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1308532 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.8668. Min Act: -0.0000

Data Index: 327549 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.6443. Min Act: -0.0000

Data Index: 454114 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.7395. Min Act: -0.0000

Data Index: 8609 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.7309. Min Act: -0.0000

Data Index: 585658 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.7042. Min Act: -0.0000

Data Index: 747222 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1129474 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1326451 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.6173. Min Act: -0.0000

Data Index: 740565 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 2.8166. Min Range: -2.8166

Max Act: 1.6217. Min Act: -0.0000

Data Index: 1330979 (C4 (Web Text))

Max Activating Token Index: 538