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

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

Neuron 1335 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: 0.1388. Min Range: -0.1388

Max Act: 0.1388. Min Act: -0.0005

Data Index: 7194 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1100. Min Act: -0.0005

Data Index: 1254034 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1203. Min Act: -0.0005

Data Index: 1061646 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1194. Min Act: -0.0005

Data Index: 916332 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1179. Min Act: -0.0005

Data Index: 657877 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1117. Min Act: -0.0004

Data Index: 431389 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1181. Min Act: -0.0005

Data Index: 319563 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1093. Min Act: -0.0004

Data Index: 1283440 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1111. Min Act: -0.0005

Data Index: 496068 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1052. Min Act: -0.0005

Data Index: 376557 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1121. Min Act: -0.0005

Data Index: 542693 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1123. Min Act: -0.0004

Data Index: 1387 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1171. Min Act: -0.0005

Data Index: 336867 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1079. Min Act: -0.0005

Data Index: 342228 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1031. Min Act: -0.0005

Data Index: 699033 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1044. Min Act: -0.0005

Data Index: 750451 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0968. Min Act: -0.0005

Data Index: 1127827 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1009. Min Act: -0.0005

Data Index: 739465 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0997. Min Act: -0.0004

Data Index: 949978 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1001. Min Act: -0.0005

Data Index: 1055687 (C4 (Web Text))

Max Activating Token Index: 340