Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0580. Min Range: -1.0580

Max Act: 1.0580. Min Act: -0.0001

Data Index: 497261 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8287. Min Act: -0.0001

Data Index: 957265 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7792. Min Act: -0.0001

Data Index: 806103 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8715. Min Act: -0.0001

Data Index: 341137 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8046. Min Act: -0.0001

Data Index: 1155186 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7991. Min Act: -0.0001

Data Index: 921383 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8158. Min Act: -0.0001

Data Index: 915314 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8163. Min Act: -0.0001

Data Index: 973118 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8335. Min Act: -0.0001

Data Index: 59721 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8224. Min Act: -0.0001

Data Index: 741389 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.8197. Min Act: -0.0001

Data Index: 905025 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7533. Min Act: -0.0001

Data Index: 140556 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7351. Min Act: -0.0001

Data Index: 750848 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7789. Min Act: -0.0001

Data Index: 956251 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7470. Min Act: -0.0001

Data Index: 1162376 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1105541 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.6250. Min Act: -0.0001

Data Index: 630004 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.6736. Min Act: -0.0001

Data Index: 315498 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.6992. Min Act: -0.0001

Data Index: 1088381 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.0580. Min Range: -1.0580

Max Act: 0.7374. Min Act: -0.0001

Data Index: 799570 (C4 (Web Text))

Max Activating Token Index: 261