Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1694 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.7985. Min Act: -0.0000

Data Index: 158936 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.7390. Min Act: -0.0000

Data Index: 236707 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.6141. Min Act: -0.0000

Data Index: 793726 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1186485 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4488. Min Act: -0.0000

Data Index: 150839 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4846. Min Act: -0.0000

Data Index: 559655 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.3751. Min Act: -0.0000

Data Index: 970452 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4538. Min Act: -0.0000

Data Index: 895087 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4427. Min Act: -0.0000

Data Index: 48977 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1072711 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.3514. Min Act: -0.0000

Data Index: 95348 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4179. Min Act: -0.0000

Data Index: 861928 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4101. Min Act: -0.0000

Data Index: 1357683 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4119. Min Act: -0.0000

Data Index: 871264 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1260720 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.3298. Min Act: -0.0000

Data Index: 456144 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.3241. Min Act: -0.0000

Data Index: 549747 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.3957. Min Act: -0.0000

Data Index: 687047 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.3824. Min Act: -0.0000

Data Index: 99264 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.7985. Min Range: -1.7985

Max Act: 1.3686. Min Act: -0.0000

Data Index: 197651 (C4 (Web Text))

Max Activating Token Index: 1004