Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0334. Min Range: -3.0334

Max Act: 3.0334. Min Act: -0.0000

Data Index: 1312586 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.3498. Min Act: -0.0000

Data Index: 1110757 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.3154. Min Act: -0.0000

Data Index: 577408 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.5426. Min Act: -0.0000

Data Index: 1197279 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.4275. Min Act: -0.0000

Data Index: 679521 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.2655. Min Act: -0.0000

Data Index: 804058 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.3180. Min Act: -0.0000

Data Index: 516112 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.2569. Min Act: -0.0000

Data Index: 168968 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.0929. Min Act: -0.0000

Data Index: 847287 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.7526. Min Act: -0.0000

Data Index: 271992 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.0378. Min Act: -0.0000

Data Index: 864020 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 3.0334. Min Range: -3.0334

Max Act: 2.0784. Min Act: -0.0000

Data Index: 1187709 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.9727. Min Act: -0.0000

Data Index: 750445 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.8504. Min Act: -0.0000

Data Index: 786994 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.8101. Min Act: -0.0000

Data Index: 1023403 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.9028. Min Act: -0.0000

Data Index: 737425 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.8973. Min Act: -0.0000

Data Index: 716352 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.7312. Min Act: -0.0000

Data Index: 203754 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.8133. Min Act: -0.0000

Data Index: 753368 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 3.0334. Min Range: -3.0334

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1160856 (C4 (Web Text))

Max Activating Token Index: 411