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

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

Neuron 2809 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6491. Min Range: -1.6491

Max Act: 1.6491. Min Act: -0.0000

Data Index: 1088501 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.6491. Min Range: -1.6491

Max Act: 1.3186. Min Act: -0.0001

Data Index: 1355791 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 1.6491. Min Range: -1.6491

Max Act: 1.1066. Min Act: -0.0000

Data Index: 461011 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 1.6491. Min Range: -1.6491

Max Act: 1.1414. Min Act: -0.0001

Data Index: 1330404 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.6491. Min Range: -1.6491

Max Act: 1.2137. Min Act: -0.0000

Data Index: 333386 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.6491. Min Range: -1.6491

Max Act: 1.1174. Min Act: -0.0000

Data Index: 155228 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1238300 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9366. Min Act: -0.0001

Data Index: 565312 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9521. Min Act: -0.0000

Data Index: 176097 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9492. Min Act: -0.0001

Data Index: 97560 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9608. Min Act: -0.0000

Data Index: 436108 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9460. Min Act: -0.0001

Data Index: 485517 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9061. Min Act: -0.0001

Data Index: 982978 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.8986. Min Act: -0.0001

Data Index: 967868 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.8710. Min Act: -0.0000

Data Index: 929811 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1034334 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.8428. Min Act: -0.0001

Data Index: 1178178 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.8704. Min Act: -0.0001

Data Index: 648683 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.8698. Min Act: -0.0000

Data Index: 607272 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.6491. Min Range: -1.6491

Max Act: 0.8612. Min Act: -0.0000

Data Index: 622411 (C4 (Web Text))

Max Activating Token Index: 109