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

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

Neuron 4847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1965. Min Range: -1.1965

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1145965 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1136081 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.9128. Min Act: -0.0000

Data Index: 895637 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.9430. Min Act: -0.0000

Data Index: 813833 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.9153. Min Act: -0.0000

Data Index: 707999 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1132366 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1096663 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8769. Min Act: -0.0000

Data Index: 788476 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8815. Min Act: -0.0000

Data Index: 853738 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1211019 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1184628 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8473. Min Act: -0.0000

Data Index: 796489 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8523. Min Act: -0.0000

Data Index: 310235 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8145. Min Act: -0.0000

Data Index: 491736 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8491. Min Act: -0.0000

Data Index: 132845 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8161. Min Act: 0.0000

Data Index: 608414 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8740. Min Act: -0.0000

Data Index: 112639 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.7837. Min Act: -0.0000

Data Index: 891011 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.8367. Min Act: -0.0000

Data Index: 141054 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 1.1965. Min Range: -1.1965

Max Act: 0.7797. Min Act: -0.0000

Data Index: 181092 (C4 (Web Text))

Max Activating Token Index: 589