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

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

Neuron 6010 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: 2.1070. Min Range: -2.1070

Max Act: 2.0917. Min Act: -0.0002

Data Index: 1245195 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 2.1070. Min Range: -2.1070

Max Act: 2.1070. Min Act: -0.0002

Data Index: 1098875 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 2.1070. Min Range: -2.1070

Max Act: 2.0159. Min Act: -0.0002

Data Index: 223988 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.9963. Min Act: -0.0002

Data Index: 423367 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.8946. Min Act: -0.0002

Data Index: 736328 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.8335. Min Act: -0.0002

Data Index: 1322604 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.8459. Min Act: -0.0002

Data Index: 828121 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.8359. Min Act: -0.0002

Data Index: 829400 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7965. Min Act: -0.0002

Data Index: 554898 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7757. Min Act: -0.0002

Data Index: 28663 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7547. Min Act: -0.0002

Data Index: 1220167 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7542. Min Act: -0.0002

Data Index: 812629 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7787. Min Act: -0.0002

Data Index: 251667 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7195. Min Act: -0.0002

Data Index: 768765 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7487. Min Act: -0.0002

Data Index: 358208 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.6927. Min Act: -0.0002

Data Index: 1178444 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7240. Min Act: -0.0002

Data Index: 388120 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7388. Min Act: -0.0002

Data Index: 1040476 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7016. Min Act: -0.0002

Data Index: 833967 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 2.1070. Min Range: -2.1070

Max Act: 1.7271. Min Act: -0.0002

Data Index: 815014 (C4 (Web Text))

Max Activating Token Index: 101