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

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

Neuron 1394 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6520. Min Act: -0.0001

Data Index: 86904 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.6079. Min Act: -0.0001

Data Index: 190928 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.4953. Min Act: -0.0000

Data Index: 205922 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.5083. Min Act: -0.0000

Data Index: 560332 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.4696. Min Act: -0.0001

Data Index: 513974 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1187949 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.4210. Min Act: -0.0001

Data Index: 1114090 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1026993 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3923. Min Act: -0.0000

Data Index: 646945 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1109448 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3794. Min Act: -0.0001

Data Index: 1294394 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3776. Min Act: -0.0000

Data Index: 523168 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3904. Min Act: -0.0001

Data Index: 1152044 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1185314 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3612. Min Act: -0.0000

Data Index: 491882 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3512. Min Act: -0.0001

Data Index: 1187643 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3476. Min Act: -0.0001

Data Index: 531661 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3321. Min Act: -0.0001

Data Index: 665644 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1330329 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.6520. Min Range: -0.6520

Max Act: 0.3353. Min Act: -0.0001

Data Index: 1129575 (C4 (Web Text))

Max Activating Token Index: 914