Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4086 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.4291. Min Act: -0.0001

Data Index: 1376436 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.4057. Min Act: -0.0001

Data Index: 1567636 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3540. Min Act: -0.0001

Data Index: 762291 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3648. Min Act: -0.0001

Data Index: 430213 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2917. Min Act: -0.0001

Data Index: 1385296 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1498658 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2997. Min Act: -0.0001

Data Index: 166475 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.3050. Min Act: -0.0001

Data Index: 1190545 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2720. Min Act: -0.0001

Data Index: 489929 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2876. Min Act: -0.0001

Data Index: 1011399 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2384. Min Act: -0.0001

Data Index: 210971 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2596. Min Act: -0.0001

Data Index: 470796 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2608. Min Act: -0.0001

Data Index: 1197696 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2603. Min Act: -0.0001

Data Index: 464440 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2634. Min Act: -0.0000

Data Index: 626429 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2469. Min Act: -0.0001

Data Index: 130787 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2520. Min Act: -0.0001

Data Index: 764858 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2514. Min Act: -0.0001

Data Index: 590 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2309. Min Act: -0.0001

Data Index: 389136 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.4291. Min Range: -0.4291

Max Act: 0.2463. Min Act: -0.0001

Data Index: 640169 (C4 (Web Text))

Max Activating Token Index: 298