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

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

Neuron 104 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: 4.3228. Min Range: -4.3228

Max Act: 4.3228. Min Act: -0.0001

Data Index: 295404 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.7318. Min Act: -0.0000

Data Index: 916716 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.0632. Min Act: -0.0000

Data Index: 556977 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.9946. Min Act: -0.0001

Data Index: 21352 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.0055. Min Act: -0.0001

Data Index: 573368 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.0676. Min Act: -0.0000

Data Index: 885388 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.0991. Min Act: -0.0000

Data Index: 588970 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.0623. Min Act: -0.0001

Data Index: 195910 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.2054. Min Act: -0.0000

Data Index: 78455 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.8793. Min Act: -0.0001

Data Index: 886579 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.9209. Min Act: -0.0000

Data Index: 588522 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.8984. Min Act: -0.0000

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.7252. Min Act: -0.0001

Data Index: 558696 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.8053. Min Act: -0.0001

Data Index: 899680 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.9937. Min Act: -0.0000

Data Index: 783141 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.1669. Min Act: -0.0000

Data Index: 1157383 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.8312. Min Act: -0.0000

Data Index: 710211 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.6625. Min Act: -0.0001

Data Index: 893943 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 4.3228. Min Range: -4.3228

Max Act: 4.1323. Min Act: -0.0001

Data Index: 1219905 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 4.3228. Min Range: -4.3228

Max Act: 3.9848. Min Act: -0.0000

Data Index: 685706 (C4 (Web Text))

Max Activating Token Index: 654