Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4415 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.8520. Min Act: -0.0000

Data Index: 815136 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5997. Min Act: -0.0000

Data Index: 464395 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5445. Min Act: -0.0000

Data Index: 900944 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.6293. Min Act: -0.0000

Data Index: 439599 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.7231. Min Act: -0.0000

Data Index: 683245 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.7166. Min Act: -0.0000

Data Index: 568580 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.6153. Min Act: -0.0000

Data Index: 433018 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5898. Min Act: -0.0000

Data Index: 453514 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5716. Min Act: -0.0000

Data Index: 411163 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5747. Min Act: -0.0000

Data Index: 902310 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5204. Min Act: -0.0000

Data Index: 141847 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4158. Min Act: -0.0000

Data Index: 804504 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4665. Min Act: -0.0000

Data Index: 673753 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4525. Min Act: -0.0000

Data Index: 909192 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4107. Min Act: -0.0000

Data Index: 284142 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4025. Min Act: -0.0000

Data Index: 495647 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3829. Min Act: -0.0000

Data Index: 200075 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3736. Min Act: -0.0000

Data Index: 876815 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3242. Min Act: -0.0000

Data Index: 725628 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3395. Min Act: -0.0000

Data Index: 85712 (C4 (Web Text))

Max Activating Token Index: 85