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

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

Neuron 5712 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: 3.3164. Min Range: -3.3164

Max Act: 3.3164. Min Act: -0.0000

Data Index: 685092 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 3.3164. Min Range: -3.3164

Max Act: 3.1303. Min Act: -0.0000

Data Index: 1223542 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 3.3164. Min Range: -3.3164

Max Act: 3.0842. Min Act: -0.0000

Data Index: 628620 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 3.3164. Min Range: -3.3164

Max Act: 3.0687. Min Act: -0.0000

Data Index: 1226058 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 3.3164. Min Range: -3.3164

Max Act: 3.0064. Min Act: -0.0000

Data Index: 804791 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.9362. Min Act: -0.0000

Data Index: 395282 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.6744. Min Act: -0.0000

Data Index: 118186 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.7802. Min Act: -0.0000

Data Index: 775807 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.6399. Min Act: -0.0000

Data Index: 769560 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.7473. Min Act: -0.0000

Data Index: 338639 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.8089. Min Act: -0.0000

Data Index: 910184 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.6509. Min Act: -0.0000

Data Index: 1261312 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.5125. Min Act: -0.0000

Data Index: 1266580 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.8798. Min Act: -0.0000

Data Index: 1017930 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.6258. Min Act: -0.0000

Data Index: 1200666 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.7294. Min Act: -0.0000

Data Index: 355295 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.5787. Min Act: -0.0000

Data Index: 656135 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.3889. Min Act: -0.0000

Data Index: 537470 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.5194. Min Act: -0.0000

Data Index: 1029923 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 3.3164. Min Range: -3.3164

Max Act: 2.6508. Min Act: -0.0000

Data Index: 796136 (C4 (Web Text))

Max Activating Token Index: 351