Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2675 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1196623 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1234102 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0106. Min Act: -0.0003

Data Index: 967081 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1135359 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0120. Min Act: -0.0003

Data Index: 933326 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0128. Min Act: -0.0003

Data Index: 146268 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0112. Min Act: -0.0003

Data Index: 898193 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0123. Min Act: -0.0003

Data Index: 118918 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0112. Min Act: -0.0003

Data Index: 820881 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0123. Min Act: -0.0003

Data Index: 282967 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1041611 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1289385 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0125. Min Act: -0.0003

Data Index: 393720 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0099. Min Act: -0.0003

Data Index: 327337 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0112. Min Act: -0.0003

Data Index: 585881 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0108. Min Act: -0.0003

Data Index: 987245 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0106. Min Act: -0.0003

Data Index: 612495 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0121. Min Act: -0.0003

Data Index: 939381 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0108. Min Act: -0.0003

Data Index: 209336 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0114. Min Act: -0.0003

Data Index: 72904 (C4 (Web Text))

Max Activating Token Index: 339