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

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

Neuron 1144 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1088. Min Act: -0.0002

Data Index: 901054 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0002

Data Index: 565478 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1015. Min Act: -0.0002

Data Index: 153802 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1026. Min Act: -0.0002

Data Index: 294159 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0984. Min Act: -0.0002

Data Index: 591111 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0928. Min Act: -0.0002

Data Index: 50776 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0958. Min Act: -0.0002

Data Index: 281278 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1311718 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0996. Min Act: -0.0002

Data Index: 520032 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0944. Min Act: -0.0002

Data Index: 163058 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0942. Min Act: -0.0002

Data Index: 803124 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0934. Min Act: -0.0002

Data Index: 314953 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1166913 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0878. Min Act: -0.0002

Data Index: 627614 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1007651 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0961. Min Act: -0.0002

Data Index: 490175 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0887. Min Act: -0.0002

Data Index: 491235 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0891. Min Act: -0.0002

Data Index: 256838 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0899. Min Act: -0.0002

Data Index: 329372 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0897. Min Act: -0.0002

Data Index: 302383 (C4 (Web Text))

Max Activating Token Index: 224