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

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

Neuron 282 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1602816 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4386. Min Act: -0.0001

Data Index: 384418 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3997. Min Act: -0.0000

Data Index: 58685 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3814. Min Act: -0.0001

Data Index: 995303 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3498. Min Act: -0.0001

Data Index: 1056325 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3394. Min Act: -0.0001

Data Index: 963792 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1447950 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1174788 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3272. Min Act: -0.0000

Data Index: 819446 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1639768 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3085. Min Act: -0.0000

Data Index: 676954 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1369389 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3256. Min Act: -0.0001

Data Index: 1547664 (Python Code)

Max Activating Token Index: 669

Text #13

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3062. Min Act: -0.0000

Data Index: 68748 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1591353 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1112379 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1596599 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1562312 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2902. Min Act: -0.0000

Data Index: 758075 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1403135 (Python Code)

Max Activating Token Index: 823