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

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

Neuron 6133 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: 0.6525. Min Range: -0.6525

Max Act: 0.6525. Min Act: -0.0000

Data Index: 145076 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.6409. Min Act: -0.0001

Data Index: 1356848 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.6408. Min Act: -0.0001

Data Index: 739046 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5772. Min Act: -0.0000

Data Index: 89326 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5293. Min Act: -0.0001

Data Index: 477085 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1093738 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5369. Min Act: -0.0000

Data Index: 13349 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1257171 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1223061 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1276984 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4891. Min Act: -0.0000

Data Index: 951679 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5076. Min Act: -0.0000

Data Index: 445980 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1197608 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1291327 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5057. Min Act: -0.0000

Data Index: 699104 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4891. Min Act: -0.0000

Data Index: 768250 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.5088. Min Act: -0.0000

Data Index: 848264 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4560. Min Act: -0.0000

Data Index: 104050 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1247450 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.6525. Min Range: -0.6525

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1057214 (C4 (Web Text))

Max Activating Token Index: 80