Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1767 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0006

Data Index: 1136560 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0915. Min Act: -0.0006

Data Index: 1018606 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0884. Min Act: -0.0006

Data Index: 711074 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0850. Min Act: -0.0006

Data Index: 259826 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0844. Min Act: -0.0006

Data Index: 214559 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0853. Min Act: -0.0006

Data Index: 235365 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0834. Min Act: -0.0006

Data Index: 898412 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0820. Min Act: -0.0005

Data Index: 328138 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0830. Min Act: -0.0006

Data Index: 1100982 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0844. Min Act: -0.0006

Data Index: 1342968 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0802. Min Act: -0.0006

Data Index: 543970 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0813. Min Act: -0.0006

Data Index: 1324170 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0774. Min Act: -0.0006

Data Index: 883914 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0786. Min Act: -0.0006

Data Index: 50430 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0779. Min Act: -0.0006

Data Index: 1204182 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0797. Min Act: -0.0006

Data Index: 576993 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0824. Min Act: -0.0006

Data Index: 1110414 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0755. Min Act: -0.0006

Data Index: 88543 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0772. Min Act: -0.0006

Data Index: 244933 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0725. Min Act: -0.0006

Data Index: 914320 (C4 (Web Text))

Max Activating Token Index: 864