Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2319 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3225. Min Act: -0.0000

Data Index: 821563 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3286. Min Act: -0.0000

Data Index: 64074 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2934. Min Act: -0.0001

Data Index: 21523 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2963. Min Act: -0.0000

Data Index: 278137 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2561. Min Act: -0.0001

Data Index: 1051204 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2706. Min Act: -0.0000

Data Index: 780603 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1158943 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2884. Min Act: -0.0001

Data Index: 927316 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2777. Min Act: -0.0001

Data Index: 680217 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1107835 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2532. Min Act: -0.0001

Data Index: 343738 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2491. Min Act: -0.0001

Data Index: 563330 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2577. Min Act: -0.0001

Data Index: 1303253 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1246329 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2464. Min Act: -0.0001

Data Index: 121231 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2608. Min Act: -0.0001

Data Index: 635475 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2467. Min Act: -0.0001

Data Index: 543382 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2279. Min Act: -0.0001

Data Index: 666873 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1031710 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2316. Min Act: -0.0001

Data Index: 644509 (C4 (Web Text))

Max Activating Token Index: 223