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

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

Neuron 3496 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: 6.4477. Min Range: -6.4477

Max Act: 6.3572. Min Act: -0.0000

Data Index: 1248936 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 6.4477. Min Range: -6.4477

Max Act: 6.4477. Min Act: -0.0000

Data Index: 786335 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 6.4477. Min Range: -6.4477

Max Act: 6.3439. Min Act: -0.0000

Data Index: 776427 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 6.4477. Min Range: -6.4477

Max Act: 6.1611. Min Act: -0.0000

Data Index: 1036897 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 6.4477. Min Range: -6.4477

Max Act: 6.2748. Min Act: -0.0001

Data Index: 329450 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 6.4477. Min Range: -6.4477

Max Act: 5.7512. Min Act: -0.0001

Data Index: 1357543 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 6.4477. Min Range: -6.4477

Max Act: 5.5038. Min Act: -0.0000

Data Index: 646922 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 6.4477. Min Range: -6.4477

Max Act: 5.7255. Min Act: -0.0000

Data Index: 1070841 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 6.4477. Min Range: -6.4477

Max Act: 5.6835. Min Act: -0.0001

Data Index: 113011 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 6.4477. Min Range: -6.4477

Max Act: 5.1620. Min Act: -0.0000

Data Index: 657915 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 6.4477. Min Range: -6.4477

Max Act: 5.1163. Min Act: -0.0000

Data Index: 301128 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.7493. Min Act: -0.0001

Data Index: 846984 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.9016. Min Act: -0.0001

Data Index: 793016 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.6435. Min Act: -0.0001

Data Index: 69431 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.8352. Min Act: -0.0000

Data Index: 115695 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.5711. Min Act: -0.0001

Data Index: 855962 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.7866. Min Act: -0.0001

Data Index: 907014 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.3382. Min Act: -0.0000

Data Index: 194950 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.0434. Min Act: -0.0001

Data Index: 395810 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 6.4477. Min Range: -6.4477

Max Act: 4.2792. Min Act: -0.0001

Data Index: 800154 (C4 (Web Text))

Max Activating Token Index: 1002