Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2963 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1329883 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.3187. Min Act: -0.0000

Data Index: 956456 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1206514 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.3148. Min Act: -0.0000

Data Index: 253501 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2737. Min Act: -0.0000

Data Index: 100833 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2930. Min Act: -0.0001

Data Index: 678347 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1013734 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2961. Min Act: -0.0001

Data Index: 833121 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2589. Min Act: -0.0000

Data Index: 656335 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2524. Min Act: -0.0001

Data Index: 345415 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2895. Min Act: -0.0000

Data Index: 512314 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1312336 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2343. Min Act: -0.0000

Data Index: 625134 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1119305 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2428. Min Act: -0.0001

Data Index: 297442 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2409. Min Act: -0.0000

Data Index: 490951 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2321. Min Act: -0.0001

Data Index: 135876 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2324. Min Act: -0.0000

Data Index: 416002 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2385. Min Act: -0.0001

Data Index: 628103 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.3599. Min Range: -0.3599

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1564013 (Python Code)

Max Activating Token Index: 599