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

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

Neuron 4521 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: 1.0231. Min Range: -1.0231

Max Act: 1.0231. Min Act: -0.0000

Data Index: 952516 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.9297. Min Act: -0.0000

Data Index: 946249 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.9298. Min Act: -0.0000

Data Index: 997207 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1150026 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8875. Min Act: -0.0000

Data Index: 970910 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8525. Min Act: -0.0000

Data Index: 474342 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.9121. Min Act: -0.0000

Data Index: 764829 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1285015 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.9524. Min Act: -0.0000

Data Index: 776897 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8204. Min Act: -0.0000

Data Index: 515029 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8374. Min Act: -0.0000

Data Index: 876192 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1156339 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8300. Min Act: -0.0000

Data Index: 645040 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1337308 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8210. Min Act: -0.0000

Data Index: 798259 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8214. Min Act: -0.0000

Data Index: 62068 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8907. Min Act: -0.0000

Data Index: 856123 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1095840 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8296. Min Act: -0.0000

Data Index: 709461 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 1.0231. Min Range: -1.0231

Max Act: 0.8326. Min Act: -0.0000

Data Index: 552119 (C4 (Web Text))

Max Activating Token Index: 819