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

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

Neuron 1074 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.8944. Min Act: -0.0000

Data Index: 393751 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.7581. Min Act: -0.0000

Data Index: 944190 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.7512. Min Act: -0.0000

Data Index: 74396 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.7211. Min Act: -0.0000

Data Index: 101031 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6841. Min Act: -0.0000

Data Index: 565676 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6572. Min Act: -0.0000

Data Index: 755230 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6454. Min Act: 0.0000

Data Index: 514476 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6638. Min Act: -0.0000

Data Index: 44339 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1221524 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6396. Min Act: -0.0000

Data Index: 422570 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1306553 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1178198 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1358572 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5746. Min Act: -0.0000

Data Index: 201811 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1054086 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5932. Min Act: -0.0000

Data Index: 179942 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1103355 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5845. Min Act: -0.0000

Data Index: 602275 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1211238 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.8944. Min Range: -0.8944

Max Act: 0.5612. Min Act: -0.0000

Data Index: 582978 (C4 (Web Text))

Max Activating Token Index: 602