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

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

Neuron 2509 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3764. Min Range: -3.3764

Max Act: 3.3367. Min Act: -0.0000

Data Index: 1027400 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 3.3764. Min Range: -3.3764

Max Act: 3.1092. Min Act: -0.0000

Data Index: 54250 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 3.3764. Min Range: -3.3764

Max Act: 3.2543. Min Act: -0.0000

Data Index: 1643950 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 3.3764. Min Range: -3.3764

Max Act: 3.3764. Min Act: -0.0000

Data Index: 1064594 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.8041. Min Act: -0.0000

Data Index: 1570271 (Python Code)

Max Activating Token Index: 839

Text #5

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.7197. Min Act: -0.0000

Data Index: 1617974 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.8650. Min Act: -0.0000

Data Index: 1567283 (Python Code)

Max Activating Token Index: 683

Text #7

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.9822. Min Act: -0.0000

Data Index: 1544096 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.5573. Min Act: -0.0000

Data Index: 1476264 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.8158. Min Act: -0.0000

Data Index: 1638075 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.6151. Min Act: -0.0000

Data Index: 218787 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.7934. Min Act: -0.0000

Data Index: 1514950 (Python Code)

Max Activating Token Index: 512

Text #12

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.6684. Min Act: -0.0000

Data Index: 1030275 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.6518. Min Act: -0.0000

Data Index: 1539328 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.5663. Min Act: -0.0000

Data Index: 1645080 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.5433. Min Act: -0.0000

Data Index: 1395792 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.7486. Min Act: -0.0000

Data Index: 1546348 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.3856. Min Act: -0.0000

Data Index: 1437087 (Python Code)

Max Activating Token Index: 669

Text #18

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.7145. Min Act: -0.0000

Data Index: 1447986 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 3.3764. Min Range: -3.3764

Max Act: 2.5961. Min Act: -0.0000

Data Index: 1470575 (Python Code)

Max Activating Token Index: 632