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

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

Neuron 3885 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.3877. Min Act: -0.0001

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.3104. Min Act: -0.0001

Data Index: 1237407 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.1160. Min Act: -0.0001

Data Index: 276557 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.1472. Min Act: -0.0001

Data Index: 1274237 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.1232. Min Act: -0.0000

Data Index: 972364 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.0985. Min Act: -0.0001

Data Index: 900662 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.0365. Min Act: -0.0001

Data Index: 567749 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9666. Min Act: -0.0001

Data Index: 232577 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9626. Min Act: -0.0000

Data Index: 44667 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1094576 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9552. Min Act: -0.0000

Data Index: 438645 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9856. Min Act: -0.0001

Data Index: 1349389 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.3877. Min Range: -1.3877

Max Act: 1.0061. Min Act: -0.0001

Data Index: 835993 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9591. Min Act: -0.0001

Data Index: 151521 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9180. Min Act: -0.0001

Data Index: 50921 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1036359 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.8906. Min Act: -0.0001

Data Index: 31403 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1100483 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.9044. Min Act: -0.0001

Data Index: 429691 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.3877. Min Range: -1.3877

Max Act: 0.8259. Min Act: -0.0001

Data Index: 1262479 (C4 (Web Text))

Max Activating Token Index: 604