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

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

Neuron 3643 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.7066. Min Act: -0.0000

Data Index: 616542 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.6606. Min Act: -0.0000

Data Index: 793811 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.6341. Min Act: -0.0000

Data Index: 611056 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1142984 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5519. Min Act: -0.0000

Data Index: 176376 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5166. Min Act: -0.0000

Data Index: 83411 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5161. Min Act: -0.0000

Data Index: 479876 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5320. Min Act: -0.0000

Data Index: 152462 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.5248. Min Act: -0.0000

Data Index: 145241 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4636. Min Act: -0.0000

Data Index: 904170 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4726. Min Act: -0.0000

Data Index: 790800 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4700. Min Act: -0.0000

Data Index: 120520 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4377. Min Act: -0.0000

Data Index: 907738 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4653. Min Act: -0.0000

Data Index: 660284 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4640. Min Act: -0.0000

Data Index: 809683 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4442. Min Act: -0.0000

Data Index: 785835 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1002211 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4546. Min Act: -0.0000

Data Index: 487505 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1201672 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.7066. Min Range: -0.7066

Max Act: 0.4495. Min Act: -0.0000

Data Index: 231144 (C4 (Web Text))

Max Activating Token Index: 605