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

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

Neuron 4468 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1249542 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0946. Min Act: -0.0002

Data Index: 854445 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1257256 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0983. Min Act: -0.0002

Data Index: 158752 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.1124. Min Act: -0.0002

Data Index: 777954 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1283109 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0951. Min Act: -0.0002

Data Index: 622131 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0852. Min Act: -0.0002

Data Index: 119802 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1082980 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0842. Min Act: -0.0002

Data Index: 877293 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0881. Min Act: -0.0002

Data Index: 132351 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1332250 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0894. Min Act: -0.0002

Data Index: 610019 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0887. Min Act: -0.0002

Data Index: 852241 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0856. Min Act: -0.0002

Data Index: 491857 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0953. Min Act: -0.0002

Data Index: 717267 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0818. Min Act: -0.0002

Data Index: 430110 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0837. Min Act: -0.0002

Data Index: 817220 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0918. Min Act: -0.0002

Data Index: 943862 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0845. Min Act: -0.0002

Data Index: 848503 (C4 (Web Text))

Max Activating Token Index: 236