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

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

Neuron 3276 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.9089. Min Act: -0.0001

Data Index: 960825 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.7543. Min Act: -0.0000

Data Index: 18877 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.7872. Min Act: -0.0000

Data Index: 916343 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.7759. Min Act: -0.0000

Data Index: 1123486 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.8309. Min Act: -0.0000

Data Index: 51477 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3064. Min Act: -0.0000

Data Index: 1274115 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.5541. Min Act: -0.0000

Data Index: 169077 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.5172. Min Act: -0.0000

Data Index: 360660 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.5886. Min Act: -0.0000

Data Index: 1355701 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.4150. Min Act: -0.0000

Data Index: 820228 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1938. Min Act: -0.0000

Data Index: 96969 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3605. Min Act: -0.0000

Data Index: 1078104 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.2351. Min Act: -0.0000

Data Index: 586613 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.6907. Min Act: -0.0000

Data Index: 269057 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3496. Min Act: -0.0000

Data Index: 683331 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3333. Min Act: -0.0000

Data Index: 849045 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3041. Min Act: -0.0000

Data Index: 1171577 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3401. Min Act: -0.0000

Data Index: 790349 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.1516. Min Act: -0.0000

Data Index: 1109852 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 2.9089. Min Range: -2.9089

Max Act: 2.3281. Min Act: -0.0000

Data Index: 1341116 (C4 (Web Text))

Max Activating Token Index: 8