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

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

Neuron 1924 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.6117. Min Act: -0.0000

Data Index: 392440 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.7410. Min Act: -0.0000

Data Index: 1093151 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.7189. Min Act: -0.0000

Data Index: 1345715 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.6002. Min Act: -0.0000

Data Index: 430274 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.5842. Min Act: -0.0000

Data Index: 923102 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.5538. Min Act: -0.0000

Data Index: 1056236 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.3304. Min Act: -0.0000

Data Index: 784207 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.3728. Min Act: -0.0000

Data Index: 386686 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.2054. Min Act: -0.0000

Data Index: 438856 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.1947. Min Act: -0.0000

Data Index: 1128374 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.1615. Min Act: -0.0000

Data Index: 69357 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.1652. Min Act: -0.0000

Data Index: 1189684 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.0099. Min Act: -0.0000

Data Index: 80962 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.1764. Min Act: -0.0000

Data Index: 1037018 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.0480. Min Act: -0.0000

Data Index: 1170005 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.0267. Min Act: -0.0000

Data Index: 1084999 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 2.7410. Min Range: -2.7410

Max Act: 1.8974. Min Act: -0.0000

Data Index: 650165 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 2.7410. Min Range: -2.7410

Max Act: 2.0988. Min Act: -0.0000

Data Index: 537774 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 2.7410. Min Range: -2.7410

Max Act: 1.9777. Min Act: -0.0000

Data Index: 1186789 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 2.7410. Min Range: -2.7410

Max Act: 1.9438. Min Act: -0.0000

Data Index: 681524 (C4 (Web Text))

Max Activating Token Index: 82