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

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

Neuron 214 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: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0000

Data Index: 807651 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0998. Min Act: -0.0000

Data Index: 52604 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0976. Min Act: -0.0000

Data Index: 171797 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1569982 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1594701 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1052. Min Act: -0.0000

Data Index: 209679 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1082. Min Act: -0.0000

Data Index: 299898 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1047. Min Act: -0.0000

Data Index: 452269 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0929. Min Act: -0.0000

Data Index: 323945 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1147624 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0944. Min Act: -0.0000

Data Index: 389187 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1439760 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1084652 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1013010 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0838. Min Act: -0.0000

Data Index: 146206 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0892. Min Act: -0.0000

Data Index: 164407 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0802. Min Act: -0.0000

Data Index: 999207 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0861. Min Act: -0.0000

Data Index: 821711 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1031106 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0874. Min Act: -0.0000

Data Index: 195620 (C4 (Web Text))

Max Activating Token Index: 562