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

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

Neuron 2266 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1091749 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7121. Min Act: -0.0000

Data Index: 938668 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7940. Min Act: -0.0000

Data Index: 305114 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6563. Min Act: -0.0000

Data Index: 200610 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6725. Min Act: -0.0001

Data Index: 168386 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7343. Min Act: -0.0000

Data Index: 390839 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1047775 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6557. Min Act: -0.0000

Data Index: 403267 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6537. Min Act: -0.0000

Data Index: 260934 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6418. Min Act: -0.0000

Data Index: 407220 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1305108 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6379. Min Act: -0.0000

Data Index: 546853 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6402. Min Act: -0.0000

Data Index: 699720 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6459. Min Act: -0.0000

Data Index: 671786 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6241. Min Act: -0.0000

Data Index: 848507 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6588. Min Act: -0.0000

Data Index: 973729 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6144. Min Act: -0.0000

Data Index: 400521 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1225252 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6318. Min Act: -0.0000

Data Index: 549083 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5980. Min Act: -0.0000

Data Index: 977595 (C4 (Web Text))

Max Activating Token Index: 125