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

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

Neuron 1018 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2609. Min Act: -0.0005

Data Index: 47421 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2399. Min Act: -0.0005

Data Index: 1036969 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2148. Min Act: -0.0005

Data Index: 8177 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2204. Min Act: -0.0005

Data Index: 501562 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2129. Min Act: -0.0005

Data Index: 639740 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2110. Min Act: -0.0005

Data Index: 381182 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2228. Min Act: -0.0005

Data Index: 1307562 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2082. Min Act: -0.0005

Data Index: 1355421 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2146. Min Act: -0.0005

Data Index: 957090 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2130. Min Act: -0.0005

Data Index: 251231 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2202. Min Act: -0.0005

Data Index: 248577 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2114. Min Act: -0.0005

Data Index: 1333558 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2117. Min Act: -0.0005

Data Index: 326240 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2042. Min Act: -0.0005

Data Index: 485945 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2032. Min Act: -0.0005

Data Index: 467188 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2177. Min Act: -0.0005

Data Index: 841785 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2094. Min Act: -0.0005

Data Index: 983682 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2233. Min Act: -0.0005

Data Index: 93887 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.2018. Min Act: -0.0005

Data Index: 6054 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.2609. Min Range: -0.2609

Max Act: 0.1958. Min Act: -0.0005

Data Index: 966954 (C4 (Web Text))

Max Activating Token Index: 573