Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1000 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1152. Min Act: -0.0001

Data Index: 2925 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1107. Min Act: -0.0001

Data Index: 191046 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0001

Data Index: 766481 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1161742 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1105. Min Act: -0.0001

Data Index: 800833 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1078419 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1067. Min Act: -0.0001

Data Index: 418598 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1026. Min Act: -0.0001

Data Index: 241010 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1063. Min Act: -0.0001

Data Index: 237498 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1008. Min Act: -0.0001

Data Index: 60833 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1035. Min Act: -0.0001

Data Index: 975415 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1029. Min Act: -0.0001

Data Index: 420790 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1012. Min Act: -0.0001

Data Index: 319458 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1173083 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0971. Min Act: -0.0001

Data Index: 156308 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1010. Min Act: -0.0001

Data Index: 911834 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0999. Min Act: -0.0001

Data Index: 662489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0991. Min Act: -0.0001

Data Index: 657155 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0997. Min Act: -0.0001

Data Index: 111377 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1063476 (C4 (Web Text))

Max Activating Token Index: 653