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

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

Neuron 1657 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.7963. Min Act: -0.0000

Data Index: 293304 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.7861. Min Act: -0.0000

Data Index: 570810 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1138353 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1076659 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1358661 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6136. Min Act: -0.0000

Data Index: 679048 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1058575 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6091. Min Act: -0.0000

Data Index: 794638 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6414. Min Act: -0.0000

Data Index: 856781 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6692. Min Act: -0.0000

Data Index: 913900 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1322992 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5928. Min Act: -0.0000

Data Index: 561867 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5886. Min Act: -0.0000

Data Index: 315076 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6005. Min Act: -0.0000

Data Index: 702303 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1310714 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5637. Min Act: -0.0000

Data Index: 733134 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5962. Min Act: -0.0001

Data Index: 1100664 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5555. Min Act: -0.0000

Data Index: 504412 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6051. Min Act: -0.0000

Data Index: 500295 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1236143 (C4 (Web Text))

Max Activating Token Index: 647