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

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

Neuron 455 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3457. Min Act: -0.0001

Data Index: 925077 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.4516. Min Act: -0.0001

Data Index: 988810 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.5910. Min Act: -0.0001

Data Index: 943450 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3924. Min Act: -0.0001

Data Index: 1225490 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3303. Min Act: -0.0001

Data Index: 770106 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.4195. Min Act: -0.0001

Data Index: 862356 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3011. Min Act: -0.0001

Data Index: 1127191 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2940. Min Act: -0.0001

Data Index: 298664 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2783. Min Act: -0.0001

Data Index: 671237 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3030. Min Act: -0.0001

Data Index: 880446 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.4070. Min Act: -0.0001

Data Index: 1254988 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3607. Min Act: -0.0001

Data Index: 562188 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2167. Min Act: -0.0002

Data Index: 723195 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3172. Min Act: -0.0001

Data Index: 317832 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.3025. Min Act: -0.0001

Data Index: 1317634 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2524. Min Act: -0.0001

Data Index: 174510 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2726. Min Act: -0.0002

Data Index: 2960 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2094. Min Act: -0.0001

Data Index: 951001 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2307. Min Act: -0.0001

Data Index: 1209458 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 1.5910. Min Range: -1.5910

Max Act: 1.2545. Min Act: -0.0001

Data Index: 348241 (C4 (Web Text))

Max Activating Token Index: 317