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

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

Neuron 4329 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.6309. Min Act: 0.0000

Data Index: 1153981 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.4230. Min Act: -0.0000

Data Index: 609007 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.3970. Min Act: 0.0000

Data Index: 48912 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.2682. Min Act: -0.0000

Data Index: 453757 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.2302. Min Act: 0.0000

Data Index: 545268 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1167849 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.6309. Min Range: -1.6309

Max Act: 1.0359. Min Act: 0.0000

Data Index: 1017084 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.9890. Min Act: -0.0000

Data Index: 905821 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.8921. Min Act: -0.0000

Data Index: 632791 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.8276. Min Act: -0.0000

Data Index: 798553 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.8221. Min Act: -0.0000

Data Index: 857996 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.8402. Min Act: -0.0000

Data Index: 366759 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.8543. Min Act: -0.0000

Data Index: 56463 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.8421. Min Act: -0.0000

Data Index: 909499 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.8455. Min Act: -0.0000

Data Index: 221158 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.7257. Min Act: -0.0000

Data Index: 916018 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.7560. Min Act: -0.0000

Data Index: 477193 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1313806 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.7632. Min Act: 0.0000

Data Index: 287334 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.6309. Min Range: -1.6309

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1278078 (C4 (Web Text))

Max Activating Token Index: 800