Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 123 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.4404. Min Act: -0.0001

Data Index: 891662 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.4052. Min Act: -0.0001

Data Index: 92005 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3907. Min Act: -0.0001

Data Index: 68759 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3680. Min Act: -0.0001

Data Index: 164930 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3482. Min Act: -0.0001

Data Index: 87907 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3553. Min Act: -0.0001

Data Index: 1242003 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3458. Min Act: -0.0001

Data Index: 1316221 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3532. Min Act: -0.0001

Data Index: 370120 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3445. Min Act: -0.0001

Data Index: 904378 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3351. Min Act: -0.0001

Data Index: 641602 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1026101 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3375. Min Act: -0.0001

Data Index: 875670 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3456. Min Act: -0.0001

Data Index: 868341 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3361. Min Act: -0.0001

Data Index: 1223006 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3371. Min Act: -0.0001

Data Index: 742415 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3323. Min Act: -0.0001

Data Index: 313054 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3304. Min Act: -0.0001

Data Index: 650614 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3309. Min Act: -0.0001

Data Index: 418332 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1306151 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.4404. Min Range: -0.4404

Max Act: 0.3254. Min Act: -0.0001

Data Index: 723470 (C4 (Web Text))

Max Activating Token Index: 181