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

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

Neuron 3539 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0366. Min Range: -1.0366

Max Act: 1.0366. Min Act: -0.0001

Data Index: 1296928 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.9683. Min Act: -0.0001

Data Index: 693993 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8803. Min Act: -0.0001

Data Index: 443586 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8817. Min Act: -0.0001

Data Index: 962455 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8331. Min Act: -0.0001

Data Index: 686760 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1307537 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7786. Min Act: -0.0001

Data Index: 1022170 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8034. Min Act: -0.0001

Data Index: 757056 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7884. Min Act: -0.0001

Data Index: 151546 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7968. Min Act: -0.0001

Data Index: 617945 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8121. Min Act: -0.0001

Data Index: 921637 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7341. Min Act: -0.0001

Data Index: 1291298 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8132. Min Act: -0.0001

Data Index: 767199 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.8091. Min Act: -0.0001

Data Index: 1308147 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7591. Min Act: -0.0001

Data Index: 681875 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1123783 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.6980. Min Act: -0.0001

Data Index: 926706 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7100. Min Act: -0.0001

Data Index: 1190123 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7445. Min Act: -0.0001

Data Index: 1053908 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.0366. Min Range: -1.0366

Max Act: 0.7125. Min Act: -0.0001

Data Index: 1626817 (Python Code)

Max Activating Token Index: 851