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

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

Neuron 488 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2699. Min Act: -0.0002

Data Index: 161585 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2690. Min Act: -0.0002

Data Index: 1114894 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2405. Min Act: -0.0001

Data Index: 962922 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2280. Min Act: 0.0000

Data Index: 1241907 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2418. Min Act: -0.0001

Data Index: 864755 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2272. Min Act: -0.0001

Data Index: 1075643 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2127. Min Act: -0.0001

Data Index: 239419 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2148. Min Act: -0.0002

Data Index: 124304 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2154. Min Act: -0.0001

Data Index: 657295 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1030167 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2197. Min Act: -0.0001

Data Index: 482623 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2083. Min Act: 0.0000

Data Index: 1074448 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2075. Min Act: -0.0001

Data Index: 954567 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2034. Min Act: -0.0001

Data Index: 218319 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1293769 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2114. Min Act: -0.0002

Data Index: 333266 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2054. Min Act: -0.0001

Data Index: 632723 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2050. Min Act: -0.0001

Data Index: 72634 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2040. Min Act: -0.0001

Data Index: 244675 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1261418 (C4 (Web Text))

Max Activating Token Index: 73