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

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

Neuron 3572 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: 0.6123. Min Range: -0.6123

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1077997 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.5793. Min Act: -0.0000

Data Index: 495951 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4410. Min Act: -0.0000

Data Index: 67807 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4000. Min Act: -0.0000

Data Index: 343121 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1095902 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1390582 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3871. Min Act: -0.0000

Data Index: 116349 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3687. Min Act: -0.0000

Data Index: 345729 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1553142 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1650193 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3538. Min Act: -0.0000

Data Index: 511941 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3455. Min Act: -0.0000

Data Index: 12768 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3337. Min Act: -0.0000

Data Index: 95490 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1628593 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1636908 (Python Code)

Max Activating Token Index: 817

Text #15

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3276. Min Act: -0.0000

Data Index: 992644 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3012. Min Act: -0.0000

Data Index: 644686 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2786. Min Act: -0.0000

Data Index: 32660 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1308762 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3041. Min Act: -0.0000

Data Index: 491830 (C4 (Web Text))

Max Activating Token Index: 559