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

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

Neuron 4628 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.8039. Min Act: -0.0000

Data Index: 425081 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.7108. Min Act: -0.0000

Data Index: 295168 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6766. Min Act: -0.0000

Data Index: 858091 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6549. Min Act: -0.0000

Data Index: 53614 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6519. Min Act: -0.0000

Data Index: 384259 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1258814 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6165. Min Act: -0.0000

Data Index: 770064 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6625. Min Act: -0.0000

Data Index: 906286 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6618. Min Act: -0.0000

Data Index: 653186 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6275. Min Act: 0.0000

Data Index: 426230 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1071409 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1191199 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1802 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1329677 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6206. Min Act: -0.0000

Data Index: 502522 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6453. Min Act: -0.0000

Data Index: 839905 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1084455 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6174. Min Act: -0.0000

Data Index: 136360 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6009. Min Act: -0.0000

Data Index: 333620 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6007. Min Act: -0.0000

Data Index: 992236 (C4 (Web Text))

Max Activating Token Index: 835