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

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

Neuron 3187 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.6514. Min Act: -0.0000

Data Index: 572112 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.7143. Min Act: -0.0000

Data Index: 417815 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.5470. Min Act: -0.0000

Data Index: 132362 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.5513. Min Act: -0.0000

Data Index: 491300 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.4663. Min Act: -0.0000

Data Index: 1344004 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.1919. Min Act: -0.0000

Data Index: 1179769 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.5232. Min Act: -0.0000

Data Index: 857022 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.2663. Min Act: -0.0000

Data Index: 449813 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.2087. Min Act: -0.0000

Data Index: 722953 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.3654. Min Act: -0.0000

Data Index: 530852 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.3220. Min Act: -0.0000

Data Index: 810823 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.3198. Min Act: -0.0000

Data Index: 85027 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.2962. Min Act: -0.0000

Data Index: 100197 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.2643. Min Act: -0.0000

Data Index: 748506 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.3267. Min Act: -0.0000

Data Index: 464893 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.3081. Min Act: -0.0000

Data Index: 135261 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0922. Min Act: -0.0000

Data Index: 1285064 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0685. Min Act: -0.0000

Data Index: 921134 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.1864. Min Act: -0.0000

Data Index: 77827 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.1644. Min Act: -0.0000

Data Index: 588232 (C4 (Web Text))

Max Activating Token Index: 366