Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 460 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0082. Min Act: -0.0006

Data Index: 38337 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0075. Min Act: -0.0006

Data Index: 439253 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0072. Min Act: -0.0006

Data Index: 694467 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0070. Min Act: -0.0006

Data Index: 155732 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1082197 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0069. Min Act: -0.0006

Data Index: 572202 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1219591 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0066. Min Act: -0.0006

Data Index: 522497 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0063. Min Act: -0.0006

Data Index: 303295 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0063. Min Act: -0.0006

Data Index: 506455 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1091197 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0062. Min Act: -0.0006

Data Index: 125348 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1264560 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0062. Min Act: -0.0006

Data Index: 779340 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0061. Min Act: -0.0006

Data Index: 625989 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1057022 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0061. Min Act: -0.0007

Data Index: 916569 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1086336 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0061. Min Act: -0.0006

Data Index: 114440 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0061. Min Act: -0.0006

Data Index: 753385 (C4 (Web Text))

Max Activating Token Index: 34