Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3281 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3077. Min Act: -0.0000

Data Index: 303806 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3130. Min Act: -0.0000

Data Index: 835464 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3150. Min Act: -0.0000

Data Index: 916307 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1292949 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.3023. Min Act: -0.0000

Data Index: 988053 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2819. Min Act: -0.0000

Data Index: 780531 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2696. Min Act: -0.0000

Data Index: 690215 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2784. Min Act: -0.0000

Data Index: 805412 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2700. Min Act: -0.0000

Data Index: 622693 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1210460 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2517. Min Act: -0.0000

Data Index: 615737 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2532. Min Act: -0.0000

Data Index: 856930 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2490. Min Act: -0.0000

Data Index: 184515 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1107296 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2550. Min Act: -0.0000

Data Index: 526980 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2429. Min Act: -0.0000

Data Index: 964490 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2320. Min Act: -0.0000

Data Index: 874296 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2324. Min Act: -0.0000

Data Index: 724486 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2216. Min Act: -0.0000

Data Index: 664420 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.3150. Min Range: -0.3150

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1205801 (C4 (Web Text))

Max Activating Token Index: 523