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

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

Neuron 1316 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2458. Min Range: -2.2458

Max Act: 2.2458. Min Act: -0.0000

Data Index: 860518 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 2.2458. Min Range: -2.2458

Max Act: 2.0938. Min Act: -0.0000

Data Index: 887683 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 2.2458. Min Range: -2.2458

Max Act: 2.0700. Min Act: -0.0000

Data Index: 426787 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 2.2458. Min Range: -2.2458

Max Act: 2.2411. Min Act: -0.0000

Data Index: 562905 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 2.2458. Min Range: -2.2458

Max Act: 2.1163. Min Act: -0.0000

Data Index: 1072168 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.9310. Min Act: -0.0000

Data Index: 703599 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.9171. Min Act: -0.0000

Data Index: 303137 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.8844. Min Act: -0.0000

Data Index: 269372 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.7527. Min Act: -0.0000

Data Index: 749790 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.7308. Min Act: -0.0000

Data Index: 834459 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.6705. Min Act: -0.0000

Data Index: 608845 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.6685. Min Act: -0.0000

Data Index: 353371 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.8513. Min Act: -0.0000

Data Index: 675838 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.7441. Min Act: -0.0000

Data Index: 1002600 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.5841. Min Act: -0.0000

Data Index: 494556 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.6136. Min Act: -0.0000

Data Index: 839216 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1346319 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.6043. Min Act: -0.0000

Data Index: 982913 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.5924. Min Act: -0.0000

Data Index: 1000930 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 2.2458. Min Range: -2.2458

Max Act: 1.5803. Min Act: -0.0000

Data Index: 200141 (C4 (Web Text))

Max Activating Token Index: 813