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

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

Neuron 4018 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: 1.0705. Min Range: -1.0705

Max Act: 1.0705. Min Act: -0.0000

Data Index: 772829 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7322. Min Act: -0.0000

Data Index: 301787 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1085986 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6507. Min Act: -0.0000

Data Index: 418646 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6452. Min Act: -0.0000

Data Index: 766601 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6019. Min Act: -0.0000

Data Index: 864383 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6027. Min Act: -0.0000

Data Index: 924285 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1347984 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1271636 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1209385 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1291723 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1199486 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5150. Min Act: -0.0000

Data Index: 385660 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4364. Min Act: -0.0000

Data Index: 739741 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4765. Min Act: -0.0000

Data Index: 782608 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4825. Min Act: -0.0000

Data Index: 631485 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1243037 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4398. Min Act: -0.0000

Data Index: 146343 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4474. Min Act: -0.0000

Data Index: 899786 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4235. Min Act: -0.0000

Data Index: 102394 (C4 (Web Text))

Max Activating Token Index: 672