Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0002

Data Index: 1109754 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1227133 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1133. Min Act: -0.0002

Data Index: 679652 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1096. Min Act: -0.0002

Data Index: 991022 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1078. Min Act: -0.0002

Data Index: 726923 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1090. Min Act: -0.0002

Data Index: 81397 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1012483 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1058. Min Act: -0.0002

Data Index: 394587 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1831 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1052. Min Act: -0.0002

Data Index: 778823 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1068. Min Act: -0.0002

Data Index: 161570 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1064. Min Act: -0.0002

Data Index: 10501 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1040. Min Act: -0.0002

Data Index: 811801 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1228811 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1044316 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1288431 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1032857 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1323639 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1101711 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1109689 (C4 (Web Text))

Max Activating Token Index: 226