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

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

Neuron 3927 in Layer 3

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: 0.3286. Min Act: -0.0001

Data Index: 1547921 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1388885 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2886. Min Act: -0.0001

Data Index: 1643861 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1519956 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2927. Min Act: -0.0001

Data Index: 1395222 (Python Code)

Max Activating Token Index: 834

Text #5

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3108. Min Act: -0.0001

Data Index: 1480202 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1511882 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1539036 (Python Code)

Max Activating Token Index: 738

Text #8

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1504774 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.3069. Min Act: -0.0001

Data Index: 1647689 (Python Code)

Max Activating Token Index: 738

Text #10

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1568251 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1607033 (Python Code)

Max Activating Token Index: 497

Text #12

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1562315 (Python Code)

Max Activating Token Index: 416

Text #13

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1529700 (Python Code)

Max Activating Token Index: 530

Text #14

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2369. Min Act: -0.0001

Data Index: 1603002 (Python Code)

Max Activating Token Index: 693

Text #15

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1531315 (Python Code)

Max Activating Token Index: 456

Text #16

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2329. Min Act: -0.0001

Data Index: 1480045 (Python Code)

Max Activating Token Index: 477

Text #17

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1406254 (Python Code)

Max Activating Token Index: 815

Text #18

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2361. Min Act: -0.0001

Data Index: 1413820 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 0.3286. Min Range: -0.3286

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1407518 (Python Code)

Max Activating Token Index: 938