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

Dataset: The Pile

Neuron 3546 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2944. Min Range: -5.2944

Max Act: 5.2159. Min Act: -0.0000

Data Index: 1752577 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 5.2944. Min Range: -5.2944

Max Act: 5.2944. Min Act: -0.0000

Data Index: 442602 (The Pile)

Max Activating Token Index: 459

Text #2

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.9350. Min Act: -0.0000

Data Index: 595510 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 5.2944. Min Range: -5.2944

Max Act: 5.0461. Min Act: -0.0000

Data Index: 1838607 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.5448. Min Act: -0.0000

Data Index: 1039195 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.4435. Min Act: -0.0000

Data Index: 219763 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.3118. Min Act: -0.0000

Data Index: 1360836 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.3367. Min Act: -0.0000

Data Index: 480539 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.1244. Min Act: -0.0000

Data Index: 1247623 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.3396. Min Act: -0.0000

Data Index: 226769 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.2961. Min Act: -0.0000

Data Index: 1202708 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.0978. Min Act: -0.0000

Data Index: 1084056 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.4260. Min Act: -0.0000

Data Index: 1557207 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.2371. Min Act: -0.0000

Data Index: 1033060 (The Pile)

Max Activating Token Index: 336

Text #14

Max Range: 5.2944. Min Range: -5.2944

Max Act: 3.7252. Min Act: -0.0000

Data Index: 1531834 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.2317. Min Act: -0.0000

Data Index: 1522989 (The Pile)

Max Activating Token Index: 645

Text #16

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.1904. Min Act: -0.0000

Data Index: 1961801 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.1927. Min Act: -0.0000

Data Index: 507737 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 5.2944. Min Range: -5.2944

Max Act: 4.1678. Min Act: -0.0000

Data Index: 54083 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 5.2944. Min Range: -5.2944

Max Act: 3.9899. Min Act: -0.0000

Data Index: 456860 (The Pile)

Max Activating Token Index: 473