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

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

Neuron 3048 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.9330. Min Act: -0.0000

Data Index: 974095 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.8669. Min Act: -0.0000

Data Index: 153839 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.8051. Min Act: -0.0000

Data Index: 773999 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3960. Min Act: -0.0000

Data Index: 66839 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.6959. Min Act: -0.0000

Data Index: 431886 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.7745. Min Act: -0.0000

Data Index: 1290083 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.5423. Min Act: -0.0000

Data Index: 161467 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4352. Min Act: -0.0000

Data Index: 578347 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4585. Min Act: -0.0000

Data Index: 1259304 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3026. Min Act: -0.0000

Data Index: 243874 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.5418. Min Act: -0.0000

Data Index: 6075 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.1795. Min Act: -0.0000

Data Index: 1100324 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.5029. Min Act: -0.0000

Data Index: 319274 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3767. Min Act: -0.0000

Data Index: 391881 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3519. Min Act: -0.0000

Data Index: 568850 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3304. Min Act: -0.0000

Data Index: 1236957 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4564. Min Act: -0.0000

Data Index: 201246 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.3006. Min Act: -0.0000

Data Index: 1234669 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.2841. Min Act: -0.0000

Data Index: 45167 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 2.9330. Min Range: -2.9330

Max Act: 2.4021. Min Act: -0.0000

Data Index: 1041762 (C4 (Web Text))

Max Activating Token Index: 875