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

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

Neuron 3377 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.6450. Min Act: -0.0000

Data Index: 482288 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.7674. Min Act: -0.0001

Data Index: 337852 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.6910. Min Act: -0.0001

Data Index: 521756 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.6020. Min Act: -0.0001

Data Index: 1220361 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5262. Min Act: -0.0001

Data Index: 751947 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4987. Min Act: -0.0000

Data Index: 531437 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4857. Min Act: -0.0000

Data Index: 573749 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3995. Min Act: -0.0001

Data Index: 40691 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3264. Min Act: -0.0000

Data Index: 783801 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4234. Min Act: -0.0001

Data Index: 1278321 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4386. Min Act: -0.0001

Data Index: 83091 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3936. Min Act: -0.0001

Data Index: 1190136 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4325. Min Act: -0.0001

Data Index: 91060 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5068. Min Act: -0.0001

Data Index: 66076 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4316. Min Act: -0.0001

Data Index: 351426 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3485. Min Act: -0.0001

Data Index: 1302216 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4122. Min Act: -0.0001

Data Index: 940513 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4960. Min Act: -0.0000

Data Index: 1144295 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5100. Min Act: -0.0000

Data Index: 331681 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4452. Min Act: -0.0001

Data Index: 1166348 (C4 (Web Text))

Max Activating Token Index: 27