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

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

Neuron 877 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: 1.8646. Min Range: -1.8646

Max Act: 1.8646. Min Act: -0.0000

Data Index: 1251423 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.6331. Min Act: -0.0000

Data Index: 1291886 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.6053. Min Act: -0.0000

Data Index: 403827 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.6038. Min Act: -0.0000

Data Index: 106963 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1064866 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1281231 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.5644. Min Act: -0.0000

Data Index: 662065 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4655. Min Act: -0.0000

Data Index: 979381 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4584. Min Act: -0.0000

Data Index: 4108 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4558. Min Act: -0.0000

Data Index: 511207 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1044995 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4313. Min Act: -0.0000

Data Index: 988228 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4893. Min Act: -0.0000

Data Index: 963028 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.3189. Min Act: -0.0000

Data Index: 450562 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.3878. Min Act: -0.0000

Data Index: 607806 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.3825. Min Act: -0.0000

Data Index: 791094 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.3821. Min Act: -0.0000

Data Index: 18534 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.3059. Min Act: -0.0000

Data Index: 244633 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.4428. Min Act: -0.0000

Data Index: 462607 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.8646. Min Range: -1.8646

Max Act: 1.3459. Min Act: -0.0000

Data Index: 980291 (C4 (Web Text))

Max Activating Token Index: 581