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

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

Neuron 4044 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 486550 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1041487 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0321. Min Act: -0.0003

Data Index: 576322 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1202742 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0307. Min Act: -0.0002

Data Index: 922637 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0331. Min Act: -0.0002

Data Index: 349321 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0307. Min Act: -0.0003

Data Index: 613054 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0305. Min Act: -0.0003

Data Index: 830220 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0313. Min Act: -0.0002

Data Index: 343215 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0287. Min Act: -0.0003

Data Index: 93902 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0292. Min Act: -0.0002

Data Index: 343237 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0285. Min Act: -0.0003

Data Index: 128538 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0295. Min Act: -0.0003

Data Index: 887821 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0298. Min Act: -0.0003

Data Index: 33222 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0307. Min Act: -0.0002

Data Index: 2094 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0263. Min Act: -0.0002

Data Index: 542821 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0280. Min Act: -0.0003

Data Index: 619256 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0276. Min Act: -0.0003

Data Index: 992768 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0275. Min Act: -0.0003

Data Index: 382440 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0258. Min Act: -0.0002

Data Index: 822564 (C4 (Web Text))

Max Activating Token Index: 386