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

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

Neuron 1296 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3604. Min Act: -0.0001

Data Index: 334065 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3343. Min Act: -0.0001

Data Index: 759125 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3069. Min Act: -0.0001

Data Index: 239287 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3054. Min Act: -0.0001

Data Index: 428681 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3063. Min Act: -0.0001

Data Index: 947185 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1355581 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3214. Min Act: -0.0001

Data Index: 1135135 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1308394 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3012. Min Act: -0.0001

Data Index: 841257 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1060260 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1209524 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.2908. Min Act: -0.0001

Data Index: 1128449 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3002. Min Act: -0.0001

Data Index: 764476 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1206677 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.2849. Min Act: -0.0001

Data Index: 947265 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.2980. Min Act: -0.0001

Data Index: 29006 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3018. Min Act: -0.0001

Data Index: 316436 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.2689. Min Act: -0.0001

Data Index: 1066980 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3145. Min Act: -0.0001

Data Index: 871710 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.2946. Min Act: -0.0001

Data Index: 1115465 (C4 (Web Text))

Max Activating Token Index: 349