Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3174 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0125. Min Range: -1.0125

Max Act: 1.0125. Min Act: -0.0001

Data Index: 783441 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9050. Min Act: -0.0001

Data Index: 42385 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.9196. Min Act: -0.0001

Data Index: 835919 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8593. Min Act: -0.0001

Data Index: 1045860 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8473. Min Act: -0.0001

Data Index: 751965 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8544. Min Act: -0.0000

Data Index: 56100 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8509. Min Act: -0.0001

Data Index: 490119 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8730. Min Act: -0.0001

Data Index: 374505 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8159. Min Act: -0.0001

Data Index: 1286715 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8372. Min Act: -0.0001

Data Index: 723112 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1029926 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7970. Min Act: -0.0001

Data Index: 137804 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8127. Min Act: -0.0001

Data Index: 723409 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8145. Min Act: -0.0001

Data Index: 1058291 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.8507. Min Act: -0.0001

Data Index: 972068 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7705. Min Act: -0.0001

Data Index: 452894 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7564. Min Act: -0.0001

Data Index: 211373 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7741. Min Act: -0.0001

Data Index: 12962 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7775. Min Act: -0.0001

Data Index: 891865 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.0125. Min Range: -1.0125

Max Act: 0.7804. Min Act: -0.0001

Data Index: 801649 (C4 (Web Text))

Max Activating Token Index: 933