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

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

Neuron 2348 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0272. Min Act: -0.0001

Data Index: 937232 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0182. Min Act: -0.0001

Data Index: 1171839 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9907. Min Act: -0.0001

Data Index: 1019136 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9552. Min Act: -0.0001

Data Index: 1331208 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9287. Min Act: -0.0001

Data Index: 855235 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9901. Min Act: -0.0001

Data Index: 190587 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9533. Min Act: -0.0001

Data Index: 838674 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8953. Min Act: -0.0001

Data Index: 502421 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9904. Min Act: -0.0001

Data Index: 775909 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8155. Min Act: -0.0001

Data Index: 222020 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8649. Min Act: -0.0001

Data Index: 1011115 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8018. Min Act: -0.0001

Data Index: 1174824 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9144. Min Act: -0.0001

Data Index: 543034 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8096. Min Act: -0.0001

Data Index: 1283560 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8758. Min Act: -0.0001

Data Index: 876736 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1285589 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8567. Min Act: -0.0001

Data Index: 28077 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8580. Min Act: -0.0001

Data Index: 1184384 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8682. Min Act: -0.0001

Data Index: 1096561 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.9142. Min Act: -0.0001

Data Index: 705236 (C4 (Web Text))

Max Activating Token Index: 120