Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5631. Min Range: -3.5631

Max Act: 3.5454. Min Act: -0.0000

Data Index: 1211031 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 3.5631. Min Range: -3.5631

Max Act: 3.5631. Min Act: -0.0000

Data Index: 967006 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.5631. Min Range: -3.5631

Max Act: 3.0299. Min Act: -0.0000

Data Index: 873271 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.9521. Min Act: -0.0000

Data Index: 223768 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.7426. Min Act: -0.0000

Data Index: 1289834 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.5892. Min Act: -0.0000

Data Index: 1019512 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.5978. Min Act: -0.0000

Data Index: 709183 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.5956. Min Act: -0.0000

Data Index: 1253400 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.5125. Min Act: -0.0000

Data Index: 712455 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.4439. Min Act: -0.0000

Data Index: 905315 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.4513. Min Act: -0.0000

Data Index: 1068456 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.4397. Min Act: -0.0000

Data Index: 1330548 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.1457. Min Act: -0.0000

Data Index: 422268 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.2499. Min Act: -0.0000

Data Index: 554652 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.3451. Min Act: -0.0000

Data Index: 11908 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.2899. Min Act: -0.0000

Data Index: 57202 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.1309. Min Act: -0.0000

Data Index: 872359 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.1721. Min Act: -0.0000

Data Index: 1180618 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.1615. Min Act: -0.0000

Data Index: 1532646 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 3.5631. Min Range: -3.5631

Max Act: 2.1141. Min Act: -0.0000

Data Index: 1008540 (C4 (Web Text))

Max Activating Token Index: 805