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

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

Neuron 4005 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: 0.9120. Min Range: -0.9120

Max Act: 0.9120. Min Act: -0.0000

Data Index: 957261 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8597. Min Act: -0.0000

Data Index: 530056 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.8574. Min Act: -0.0000

Data Index: 443297 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7828. Min Act: -0.0000

Data Index: 122636 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7503. Min Act: -0.0000

Data Index: 150912 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7167. Min Act: -0.0000

Data Index: 586314 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1189708 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1112938 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6963. Min Act: -0.0000

Data Index: 492628 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6461. Min Act: -0.0000

Data Index: 198240 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6370. Min Act: -0.0000

Data Index: 483077 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6280. Min Act: -0.0000

Data Index: 757020 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6134. Min Act: -0.0000

Data Index: 190214 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.6068. Min Act: -0.0000

Data Index: 827944 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5727. Min Act: -0.0000

Data Index: 314866 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5708. Min Act: -0.0000

Data Index: 353944 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5520. Min Act: -0.0000

Data Index: 810953 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1089211 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1246880 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.9120. Min Range: -0.9120

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1153768 (C4 (Web Text))

Max Activating Token Index: 337