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

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

Neuron 648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4938. Min Range: -2.4938

Max Act: 2.4938. Min Act: -0.0000

Data Index: 1302462 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 2.4938. Min Range: -2.4938

Max Act: 2.1048. Min Act: -0.0000

Data Index: 923793 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.9097. Min Act: -0.0000

Data Index: 401923 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.9610. Min Act: -0.0000

Data Index: 437980 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1182612 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7756. Min Act: -0.0000

Data Index: 292603 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7796. Min Act: -0.0000

Data Index: 707474 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.8819. Min Act: -0.0000

Data Index: 383694 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.8600. Min Act: -0.0000

Data Index: 384184 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7521. Min Act: -0.0000

Data Index: 45063 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.6436. Min Act: -0.0000

Data Index: 839 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.6505. Min Act: -0.0000

Data Index: 162886 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7371. Min Act: 0.0000

Data Index: 1062268 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7230. Min Act: -0.0000

Data Index: 466756 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1302883 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.8005. Min Act: -0.0000

Data Index: 659239 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7875. Min Act: -0.0000

Data Index: 922938 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.6871. Min Act: -0.0000

Data Index: 1060225 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.7339. Min Act: -0.0000

Data Index: 133104 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 2.4938. Min Range: -2.4938

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1067159 (C4 (Web Text))

Max Activating Token Index: 932