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

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

Neuron 2800 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: 1.2794. Min Range: -1.2794

Max Act: 1.2794. Min Act: -0.0001

Data Index: 414 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.1521. Min Act: -0.0001

Data Index: 1051476 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.2794. Min Range: -1.2794

Max Act: 1.0849. Min Act: -0.0001

Data Index: 317060 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.8983. Min Act: -0.0002

Data Index: 667150 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.9174. Min Act: -0.0001

Data Index: 467380 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.9203. Min Act: -0.0001

Data Index: 619249 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1185300 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.9638. Min Act: -0.0002

Data Index: 1262972 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.8403. Min Act: -0.0002

Data Index: 1106015 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.8933. Min Act: -0.0001

Data Index: 1280289 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.8852. Min Act: -0.0001

Data Index: 1337936 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.7524. Min Act: -0.0001

Data Index: 876224 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.9023. Min Act: -0.0001

Data Index: 317798 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.8285. Min Act: -0.0002

Data Index: 1045049 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.9075. Min Act: -0.0002

Data Index: 971767 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.8891. Min Act: -0.0002

Data Index: 512002 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.7735. Min Act: -0.0002

Data Index: 498294 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.8438. Min Act: -0.0001

Data Index: 626161 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.7898. Min Act: -0.0002

Data Index: 155582 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.2794. Min Range: -1.2794

Max Act: 0.9059. Min Act: -0.0002

Data Index: 497975 (C4 (Web Text))

Max Activating Token Index: 141