Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3934 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.5223. Min Act: -0.0000

Data Index: 268095 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.4192. Min Act: -0.0000

Data Index: 84064 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.4920. Min Act: -0.0000

Data Index: 121925 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1022442 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.4379. Min Act: -0.0000

Data Index: 156852 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.4131. Min Act: -0.0000

Data Index: 222552 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1035225 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.2769. Min Act: -0.0000

Data Index: 709903 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.3085. Min Act: -0.0000

Data Index: 828185 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.3029. Min Act: -0.0000

Data Index: 366574 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.3683. Min Act: -0.0000

Data Index: 367995 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.3256. Min Act: -0.0000

Data Index: 1326544 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.3550. Min Act: -0.0000

Data Index: 413619 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.2760. Min Act: -0.0000

Data Index: 1214854 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.3033. Min Act: -0.0000

Data Index: 992827 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1104530 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.2388. Min Act: -0.0000

Data Index: 654311 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.1888. Min Act: -0.0000

Data Index: 186354 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1236402 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.5223. Min Range: -1.5223

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1238848 (C4 (Web Text))

Max Activating Token Index: 400