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

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

Neuron 2840 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.5939. Min Act: -0.0001

Data Index: 330526 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4627. Min Act: -0.0001

Data Index: 679963 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4609. Min Act: -0.0001

Data Index: 681074 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4312. Min Act: -0.0001

Data Index: 538267 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4476. Min Act: -0.0001

Data Index: 321031 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4119. Min Act: -0.0001

Data Index: 1304324 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4261. Min Act: -0.0001

Data Index: 577314 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4134. Min Act: -0.0001

Data Index: 522985 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3927. Min Act: -0.0001

Data Index: 885706 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3898. Min Act: -0.0001

Data Index: 128851 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4221. Min Act: -0.0001

Data Index: 1225953 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4103. Min Act: -0.0001

Data Index: 1265611 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4030. Min Act: -0.0001

Data Index: 1172161 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3759. Min Act: -0.0001

Data Index: 664130 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3983. Min Act: -0.0001

Data Index: 894134 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3916. Min Act: -0.0001

Data Index: 1250340 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1156832 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3608. Min Act: -0.0001

Data Index: 731499 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3588. Min Act: -0.0001

Data Index: 14218 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.5939. Min Range: -0.5939

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1210867 (C4 (Web Text))

Max Activating Token Index: 632