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

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

Neuron 318 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2988. Min Act: -0.0000

Data Index: 896790 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1001887 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2830. Min Act: -0.0000

Data Index: 345794 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2626. Min Act: -0.0000

Data Index: 169841 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2520. Min Act: -0.0000

Data Index: 799169 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2287. Min Act: -0.0000

Data Index: 964617 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2285. Min Act: -0.0000

Data Index: 564595 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2190. Min Act: -0.0000

Data Index: 513680 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2136. Min Act: -0.0000

Data Index: 842164 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2189. Min Act: -0.0000

Data Index: 528403 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2108. Min Act: -0.0000

Data Index: 706694 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2069. Min Act: -0.0000

Data Index: 442717 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2132. Min Act: -0.0000

Data Index: 50573 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1971. Min Act: -0.0000

Data Index: 763250 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2054. Min Act: -0.0000

Data Index: 788079 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1951. Min Act: -0.0000

Data Index: 881173 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2038. Min Act: -0.0000

Data Index: 976842 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1963. Min Act: -0.0000

Data Index: 26064 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2313. Min Act: -0.0000

Data Index: 302094 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1146178 (C4 (Web Text))

Max Activating Token Index: 261