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

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

Neuron 1333 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.7102. Min Act: -0.0001

Data Index: 1191444 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6696. Min Act: -0.0001

Data Index: 850599 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.6514. Min Act: -0.0001

Data Index: 547192 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5914. Min Act: -0.0001

Data Index: 864893 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5997. Min Act: -0.0001

Data Index: 387105 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5699. Min Act: -0.0001

Data Index: 11187 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5714. Min Act: -0.0001

Data Index: 474426 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5531. Min Act: -0.0001

Data Index: 1273533 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5509. Min Act: -0.0001

Data Index: 649126 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5613. Min Act: -0.0001

Data Index: 580640 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5529. Min Act: -0.0001

Data Index: 9804 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5253. Min Act: -0.0001

Data Index: 983135 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5358. Min Act: -0.0001

Data Index: 343115 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4826. Min Act: -0.0001

Data Index: 571897 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5193. Min Act: -0.0001

Data Index: 1240042 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.4963. Min Act: -0.0001

Data Index: 794755 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5153. Min Act: -0.0001

Data Index: 63958 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5125. Min Act: -0.0001

Data Index: 1171516 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5310. Min Act: -0.0001

Data Index: 901789 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.7102. Min Range: -0.7102

Max Act: 0.5105. Min Act: -0.0001

Data Index: 1102586 (C4 (Web Text))

Max Activating Token Index: 43