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

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

Neuron 3477 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.9453. Min Act: -0.0001

Data Index: 955600 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6848. Min Act: -0.0001

Data Index: 1334568 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6180. Min Act: -0.0001

Data Index: 876562 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6050. Min Act: -0.0001

Data Index: 154329 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6129. Min Act: -0.0001

Data Index: 1215962 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5821. Min Act: -0.0001

Data Index: 610174 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.6150. Min Act: -0.0001

Data Index: 786374 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5907. Min Act: -0.0001

Data Index: 217027 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5942. Min Act: -0.0001

Data Index: 1280456 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5787. Min Act: -0.0001

Data Index: 395445 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5888. Min Act: -0.0001

Data Index: 475307 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5515. Min Act: -0.0001

Data Index: 150076 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5431. Min Act: -0.0001

Data Index: 1169248 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5618. Min Act: -0.0001

Data Index: 939165 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.4974. Min Act: -0.0001

Data Index: 1062916 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5565. Min Act: -0.0001

Data Index: 673972 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5410. Min Act: -0.0001

Data Index: 339731 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5522. Min Act: -0.0001

Data Index: 613261 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5406. Min Act: -0.0001

Data Index: 1048811 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.9453. Min Range: -0.9453

Max Act: 0.5132. Min Act: -0.0001

Data Index: 185848 (C4 (Web Text))

Max Activating Token Index: 707