Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 532 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0121. Min Act: -0.0005

Data Index: 784183 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0114. Min Act: -0.0005

Data Index: 107117 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0117. Min Act: -0.0005

Data Index: 977295 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1637128 (Python Code)

Max Activating Token Index: 316

Text #4

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0104. Min Act: -0.0005

Data Index: 969127 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1288301 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0103. Min Act: -0.0005

Data Index: 1257157 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0101. Min Act: -0.0005

Data Index: 787817 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0005

Data Index: 51009 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0005

Data Index: 928855 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0005

Data Index: 83879 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0101. Min Act: -0.0005

Data Index: 604294 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0005

Data Index: 802492 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0098. Min Act: -0.0005

Data Index: 737218 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0099. Min Act: -0.0005

Data Index: 119878 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0097. Min Act: -0.0005

Data Index: 882474 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0097. Min Act: -0.0005

Data Index: 817439 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0097. Min Act: -0.0005

Data Index: 1123818 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0097. Min Act: -0.0005

Data Index: 148336 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0093. Min Act: -0.0005

Data Index: 941739 (C4 (Web Text))

Max Activating Token Index: 950