Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1616 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1184. Min Act: -0.0006

Data Index: 9430 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1019. Min Act: -0.0006

Data Index: 748399 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1061. Min Act: -0.0006

Data Index: 112736 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1048. Min Act: -0.0006

Data Index: 382587 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0971. Min Act: -0.0006

Data Index: 683414 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0933. Min Act: -0.0006

Data Index: 1047224 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0961. Min Act: -0.0006

Data Index: 741855 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0886. Min Act: -0.0006

Data Index: 482821 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1157. Min Act: -0.0006

Data Index: 464086 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0949. Min Act: -0.0006

Data Index: 654276 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0912. Min Act: -0.0006

Data Index: 841928 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0899. Min Act: -0.0006

Data Index: 1069302 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0931. Min Act: -0.0006

Data Index: 463874 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0824. Min Act: -0.0006

Data Index: 1161421 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0892. Min Act: -0.0006

Data Index: 503864 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0884. Min Act: -0.0006

Data Index: 1015784 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0886. Min Act: -0.0006

Data Index: 1113853 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0814. Min Act: -0.0006

Data Index: 127289 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0901. Min Act: -0.0006

Data Index: 410002 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0938. Min Act: -0.0006

Data Index: 1191628 (C4 (Web Text))

Max Activating Token Index: 415