Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1653 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0132. Min Act: -0.0003

Data Index: 639113 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0003

Data Index: 87707 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0004

Data Index: 509511 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0003

Data Index: 547429 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0004

Data Index: 846066 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0114. Min Act: -0.0003

Data Index: 196543 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0115. Min Act: -0.0003

Data Index: 836491 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0004

Data Index: 375972 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0003

Data Index: 592696 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0111. Min Act: -0.0003

Data Index: 950412 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0003

Data Index: 925995 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0110. Min Act: -0.0003

Data Index: 259734 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0109. Min Act: -0.0003

Data Index: 311932 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0109. Min Act: -0.0004

Data Index: 1197018 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0109. Min Act: -0.0003

Data Index: 90344 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0004

Data Index: 108388 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1324431 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0105. Min Act: -0.0003

Data Index: 290792 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1358592 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0103. Min Act: -0.0004

Data Index: 730014 (C4 (Web Text))

Max Activating Token Index: 320