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

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

Neuron 1063 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.1289. Min Act: -0.0001

Data Index: 439616 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.0332. Min Act: -0.0001

Data Index: 1192557 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8772. Min Act: -0.0000

Data Index: 182956 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8625. Min Act: -0.0001

Data Index: 1046152 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8681. Min Act: -0.0001

Data Index: 838291 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8164. Min Act: -0.0001

Data Index: 1223545 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7803. Min Act: -0.0001

Data Index: 1172962 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8081. Min Act: -0.0001

Data Index: 388914 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8331. Min Act: -0.0001

Data Index: 594552 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7987. Min Act: -0.0001

Data Index: 785203 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7841. Min Act: -0.0001

Data Index: 983317 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7825. Min Act: -0.0001

Data Index: 230834 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8036. Min Act: -0.0001

Data Index: 1238824 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7763. Min Act: -0.0001

Data Index: 478214 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7336. Min Act: -0.0001

Data Index: 741521 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7596. Min Act: -0.0001

Data Index: 722151 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8004. Min Act: -0.0001

Data Index: 54338 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7470. Min Act: -0.0001

Data Index: 775936 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7654. Min Act: -0.0001

Data Index: 92554 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7448. Min Act: -0.0001

Data Index: 675682 (C4 (Web Text))

Max Activating Token Index: 928