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

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

Neuron 2607 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.5307. Min Act: -0.0001

Data Index: 970085 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4648. Min Act: -0.0001

Data Index: 315006 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.5088. Min Act: -0.0002

Data Index: 563485 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.5003. Min Act: -0.0002

Data Index: 444872 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4432. Min Act: -0.0001

Data Index: 696446 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4822. Min Act: -0.0002

Data Index: 851970 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4160. Min Act: -0.0001

Data Index: 132054 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4207. Min Act: -0.0002

Data Index: 460266 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4462. Min Act: -0.0002

Data Index: 317232 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4597. Min Act: -0.0001

Data Index: 988635 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4404. Min Act: -0.0001

Data Index: 857024 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4277. Min Act: -0.0002

Data Index: 126746 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.3926. Min Act: -0.0001

Data Index: 622272 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4174. Min Act: -0.0002

Data Index: 1007452 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4033. Min Act: -0.0002

Data Index: 257145 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4108. Min Act: -0.0002

Data Index: 784115 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4249. Min Act: -0.0002

Data Index: 643509 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.3931. Min Act: -0.0001

Data Index: 1116358 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.3930. Min Act: -0.0001

Data Index: 874350 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.5307. Min Range: -0.5307

Max Act: 0.4042. Min Act: -0.0002

Data Index: 437877 (C4 (Web Text))

Max Activating Token Index: 716