Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1715 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.4054. Min Act: -0.0001

Data Index: 481512 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3471. Min Act: -0.0001

Data Index: 410916 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3504. Min Act: -0.0001

Data Index: 409241 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3396. Min Act: -0.0001

Data Index: 1270138 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3371. Min Act: -0.0001

Data Index: 271681 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3321. Min Act: -0.0001

Data Index: 89146 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3416. Min Act: -0.0001

Data Index: 1333741 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3265. Min Act: -0.0001

Data Index: 1099679 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3290. Min Act: -0.0001

Data Index: 795053 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3159. Min Act: -0.0001

Data Index: 1299912 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3233. Min Act: -0.0001

Data Index: 413644 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3159. Min Act: -0.0001

Data Index: 119733 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3128. Min Act: -0.0001

Data Index: 230334 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3128. Min Act: -0.0001

Data Index: 233816 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3077. Min Act: -0.0001

Data Index: 138513 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3128. Min Act: -0.0001

Data Index: 1101070 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3149. Min Act: -0.0001

Data Index: 524484 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2724. Min Act: -0.0001

Data Index: 814883 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.3141. Min Act: -0.0001

Data Index: 589650 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.4054. Min Range: -0.4054

Max Act: 0.2979. Min Act: -0.0001

Data Index: 624435 (C4 (Web Text))

Max Activating Token Index: 675