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

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

Neuron 4035 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1180446 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5049. Min Act: 0.0000

Data Index: 1200954 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1150716 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1179164 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4952. Min Act: -0.0000

Data Index: 929209 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5059. Min Act: -0.0000

Data Index: 555532 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.5128. Min Act: -0.0000

Data Index: 821367 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4736. Min Act: -0.0000

Data Index: 521719 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1329011 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4662. Min Act: -0.0000

Data Index: 137354 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4511. Min Act: 0.0000

Data Index: 801514 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4662. Min Act: -0.0000

Data Index: 651825 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4488. Min Act: 0.0000

Data Index: 251213 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4786. Min Act: -0.0000

Data Index: 466494 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4493. Min Act: -0.0000

Data Index: 302272 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4598. Min Act: -0.0000

Data Index: 211648 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1049887 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4554. Min Act: -0.0000

Data Index: 173371 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1207708 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.5700. Min Range: -0.5700

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1171402 (C4 (Web Text))

Max Activating Token Index: 491