Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4997 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4807. Min Act: -0.0000

Data Index: 821048 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.5015. Min Act: -0.0000

Data Index: 813691 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4242. Min Act: -0.0000

Data Index: 956740 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4293. Min Act: -0.0000

Data Index: 824003 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1282666 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1327633 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.4040. Min Act: -0.0000

Data Index: 615543 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3692. Min Act: -0.0000

Data Index: 377018 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3533. Min Act: -0.0000

Data Index: 266706 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3458. Min Act: -0.0000

Data Index: 592100 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3318. Min Act: -0.0000

Data Index: 454927 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3162. Min Act: -0.0000

Data Index: 593391 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1174888 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.2959. Min Act: -0.0000

Data Index: 377577 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1265405 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1273916 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1287449 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.2939. Min Act: -0.0000

Data Index: 275647 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1001082 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.5015. Min Range: -0.5015

Max Act: 0.2907. Min Act: -0.0000

Data Index: 428850 (C4 (Web Text))

Max Activating Token Index: 632