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

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

Neuron 261 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0002

Data Index: 947962 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0342. Min Act: -0.0002

Data Index: 367385 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0328. Min Act: -0.0002

Data Index: 653490 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0344. Min Act: -0.0002

Data Index: 434523 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0316. Min Act: -0.0002

Data Index: 158789 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0330. Min Act: -0.0002

Data Index: 664755 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0327. Min Act: -0.0002

Data Index: 81600 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1203046 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0305. Min Act: -0.0002

Data Index: 185997 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0305. Min Act: -0.0002

Data Index: 918035 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1212842 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1070202 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0312. Min Act: -0.0002

Data Index: 550738 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0318. Min Act: -0.0002

Data Index: 216312 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0310. Min Act: -0.0002

Data Index: 957867 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0313. Min Act: -0.0002

Data Index: 254571 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1067924 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1225530 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0301. Min Act: -0.0002

Data Index: 953987 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0290. Min Act: -0.0002

Data Index: 15150 (C4 (Web Text))

Max Activating Token Index: 511