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

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

Neuron 4537 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: 1.0091. Min Range: -1.0091

Max Act: 1.0091. Min Act: -0.0000

Data Index: 1267734 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.8536. Min Act: -0.0000

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.8798. Min Act: -0.0000

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1079983 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7728. Min Act: -0.0000

Data Index: 143173 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7661. Min Act: -0.0000

Data Index: 247070 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1294455 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7997. Min Act: -0.0000

Data Index: 737356 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7422. Min Act: -0.0000

Data Index: 813743 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7673. Min Act: -0.0000

Data Index: 988511 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1286980 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1630523 (Python Code)

Max Activating Token Index: 500

Text #12

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.6698. Min Act: -0.0000

Data Index: 973804 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1265384 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7386. Min Act: -0.0000

Data Index: 223085 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7559. Min Act: -0.0000

Data Index: 767853 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1051352 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1002188 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.0091. Min Range: -1.0091

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1225158 (C4 (Web Text))

Max Activating Token Index: 294