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

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

Neuron 1396 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: 1.0160. Min Range: -1.0160

Max Act: 1.0160. Min Act: -0.0000

Data Index: 232447 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.8449. Min Act: -0.0000

Data Index: 909627 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.7742. Min Act: -0.0000

Data Index: 967708 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.7188. Min Act: -0.0000

Data Index: 891114 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1132831 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6461. Min Act: -0.0000

Data Index: 433676 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6359. Min Act: -0.0000

Data Index: 651789 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1318737 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6029. Min Act: -0.0000

Data Index: 524809 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.6092. Min Act: -0.0001

Data Index: 30224 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1223053 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5502. Min Act: -0.0000

Data Index: 687012 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5840. Min Act: -0.0001

Data Index: 906737 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5467. Min Act: -0.0000

Data Index: 374849 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5773. Min Act: -0.0001

Data Index: 1069740 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5597. Min Act: -0.0000

Data Index: 318319 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5385. Min Act: -0.0000

Data Index: 55186 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5312. Min Act: -0.0001

Data Index: 189358 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5460. Min Act: -0.0000

Data Index: 4847 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 1.0160. Min Range: -1.0160

Max Act: 0.5297. Min Act: -0.0001

Data Index: 588286 (C4 (Web Text))

Max Activating Token Index: 29