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

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

Neuron 3480 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: 0.3596. Min Range: -0.3596

Max Act: 0.3596. Min Act: -0.0001

Data Index: 185497 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3363. Min Act: -0.0001

Data Index: 779405 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3381. Min Act: -0.0001

Data Index: 232445 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3155. Min Act: -0.0001

Data Index: 555205 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3124. Min Act: -0.0001

Data Index: 548138 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3107. Min Act: -0.0001

Data Index: 713917 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2930. Min Act: -0.0001

Data Index: 71030 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3091. Min Act: -0.0001

Data Index: 699020 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3316. Min Act: -0.0001

Data Index: 757125 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2867. Min Act: -0.0001

Data Index: 123913 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2855. Min Act: -0.0001

Data Index: 215328 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.3031. Min Act: -0.0001

Data Index: 840066 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2574. Min Act: -0.0001

Data Index: 51114 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2821. Min Act: -0.0001

Data Index: 409405 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1032961 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2788. Min Act: -0.0001

Data Index: 546768 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1323693 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2760. Min Act: -0.0001

Data Index: 268975 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2553. Min Act: -0.0001

Data Index: 820428 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.3596. Min Range: -0.3596

Max Act: 0.2645. Min Act: -0.0001

Data Index: 553932 (C4 (Web Text))

Max Activating Token Index: 582