Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 305 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.1802. Min Range: -3.1802

Max Act: 3.1802. Min Act: -0.0001

Data Index: 207802 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8618. Min Act: -0.0001

Data Index: 24440 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.9683. Min Act: -0.0001

Data Index: 1233113 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8078. Min Act: -0.0001

Data Index: 269403 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8084. Min Act: -0.0001

Data Index: 659073 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.8212. Min Act: -0.0001

Data Index: 773257 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.7787. Min Act: -0.0001

Data Index: 770741 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.7476. Min Act: -0.0001

Data Index: 1187939 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.5181. Min Act: -0.0001

Data Index: 352449 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.7569. Min Act: -0.0001

Data Index: 733706 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.7083. Min Act: -0.0001

Data Index: 231699 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.4057. Min Act: -0.0001

Data Index: 483930 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.3850. Min Act: -0.0001

Data Index: 1056052 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.3549. Min Act: -0.0001

Data Index: 629769 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.5814. Min Act: -0.0001

Data Index: 43535 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.3384. Min Act: -0.0001

Data Index: 787125 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.4532. Min Act: -0.0001

Data Index: 887109 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.4537. Min Act: -0.0001

Data Index: 352009 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.3968. Min Act: -0.0001

Data Index: 174943 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.1802. Min Range: -3.1802

Max Act: 2.5147. Min Act: -0.0001

Data Index: 895142 (C4 (Web Text))

Max Activating Token Index: 7