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

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

Neuron 3154 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: 0.4409. Min Range: -0.4409

Max Act: 0.4409. Min Act: -0.0001

Data Index: 1222996 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3315. Min Act: -0.0001

Data Index: 598204 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1322755 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3478. Min Act: -0.0000

Data Index: 683489 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3372. Min Act: -0.0000

Data Index: 987130 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3571. Min Act: -0.0000

Data Index: 804512 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2920. Min Act: -0.0001

Data Index: 790118 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2901. Min Act: -0.0001

Data Index: 264890 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2982. Min Act: -0.0001

Data Index: 708727 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2606. Min Act: -0.0000

Data Index: 145423 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2654. Min Act: -0.0000

Data Index: 503647 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2863. Min Act: -0.0000

Data Index: 128614 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2290. Min Act: -0.0000

Data Index: 900383 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.3167. Min Act: -0.0001

Data Index: 780982 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2707. Min Act: -0.0001

Data Index: 174932 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2801. Min Act: -0.0001

Data Index: 385304 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2653. Min Act: -0.0001

Data Index: 151022 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2469. Min Act: -0.0001

Data Index: 281258 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2496. Min Act: -0.0001

Data Index: 268780 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.4409. Min Range: -0.4409

Max Act: 0.2220. Min Act: -0.0001

Data Index: 414544 (C4 (Web Text))

Max Activating Token Index: 905