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

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

Neuron 3923 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8927. Min Act: -0.0000

Data Index: 55672 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8143. Min Act: -0.0000

Data Index: 706485 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8236. Min Act: -0.0000

Data Index: 604582 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7656. Min Act: -0.0000

Data Index: 987074 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1157711 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7531. Min Act: -0.0000

Data Index: 70990 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8116. Min Act: -0.0000

Data Index: 197979 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7375. Min Act: -0.0000

Data Index: 413686 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1288112 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7774. Min Act: -0.0000

Data Index: 959659 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7770. Min Act: -0.0000

Data Index: 827823 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7098. Min Act: -0.0000

Data Index: 307823 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7507. Min Act: -0.0000

Data Index: 351668 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1113670 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7484. Min Act: -0.0000

Data Index: 74340 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7456. Min Act: -0.0000

Data Index: 476044 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7403. Min Act: -0.0000

Data Index: 518392 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7362. Min Act: -0.0000

Data Index: 672509 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1317055 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7223. Min Act: -0.0000

Data Index: 436801 (C4 (Web Text))

Max Activating Token Index: 160