Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2495 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1448. Min Act: -0.0003

Data Index: 201076 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1273. Min Act: -0.0003

Data Index: 903997 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1279. Min Act: -0.0003

Data Index: 770385 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1192. Min Act: -0.0003

Data Index: 1171870 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1120. Min Act: -0.0003

Data Index: 285448 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1108. Min Act: -0.0003

Data Index: 213194 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1079. Min Act: -0.0003

Data Index: 576313 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1073. Min Act: -0.0003

Data Index: 510024 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1062. Min Act: -0.0003

Data Index: 813720 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1095. Min Act: -0.0003

Data Index: 575974 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1013. Min Act: -0.0003

Data Index: 112508 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1044. Min Act: -0.0003

Data Index: 1217282 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1091. Min Act: -0.0003

Data Index: 470451 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0962. Min Act: -0.0003

Data Index: 641924 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0959. Min Act: -0.0003

Data Index: 71114 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0982. Min Act: -0.0003

Data Index: 741304 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0978. Min Act: -0.0003

Data Index: 182654 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0973. Min Act: -0.0003

Data Index: 1126546 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.1047. Min Act: -0.0003

Data Index: 347209 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.1448. Min Range: -0.1448

Max Act: 0.0957. Min Act: -0.0003

Data Index: 118731 (C4 (Web Text))

Max Activating Token Index: 32