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

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

Neuron 803 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.6835. Min Act: -0.0000

Data Index: 441167 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.5409. Min Act: -0.0000

Data Index: 1244706 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.5299. Min Act: -0.0000

Data Index: 957835 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.2901. Min Act: -0.0000

Data Index: 1250248 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.2926. Min Act: -0.0000

Data Index: 1234693 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.3210. Min Act: -0.0000

Data Index: 34051 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.0180. Min Act: -0.0000

Data Index: 683215 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 2.6835. Min Range: -2.6835

Max Act: 2.0586. Min Act: -0.0000

Data Index: 1162910 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.9004. Min Act: -0.0000

Data Index: 275361 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.7384. Min Act: -0.0000

Data Index: 318062 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.8819. Min Act: -0.0000

Data Index: 633078 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.7529. Min Act: -0.0000

Data Index: 527856 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.7503. Min Act: -0.0000

Data Index: 1097434 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.8453. Min Act: -0.0000

Data Index: 536573 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.7256. Min Act: -0.0000

Data Index: 804226 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.8016. Min Act: -0.0000

Data Index: 195620 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.8005. Min Act: -0.0000

Data Index: 185212 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.8701. Min Act: -0.0000

Data Index: 95903 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.7471. Min Act: -0.0000

Data Index: 462536 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 2.6835. Min Range: -2.6835

Max Act: 1.6311. Min Act: -0.0000

Data Index: 835874 (C4 (Web Text))

Max Activating Token Index: 438