Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8135. Min Range: -4.8135

Max Act: 4.8135. Min Act: -0.0000

Data Index: 1029499 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.5350. Min Act: -0.0000

Data Index: 168364 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.5123. Min Act: -0.0000

Data Index: 287005 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.1910. Min Act: -0.0000

Data Index: 1350261 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.4870. Min Act: -0.0000

Data Index: 653713 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.2061. Min Act: -0.0000

Data Index: 241146 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.0841. Min Act: -0.0000

Data Index: 41162 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.1437. Min Act: -0.0000

Data Index: 843523 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 4.8135. Min Range: -4.8135

Max Act: 2.9846. Min Act: -0.0000

Data Index: 280323 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.1356. Min Act: -0.0000

Data Index: 427085 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 4.8135. Min Range: -4.8135

Max Act: 2.6532. Min Act: -0.0000

Data Index: 241862 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.1355. Min Act: -0.0000

Data Index: 1133984 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.0832. Min Act: -0.0000

Data Index: 834235 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 4.8135. Min Range: -4.8135

Max Act: 2.6056. Min Act: -0.0000

Data Index: 620900 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 4.8135. Min Range: -4.8135

Max Act: 2.8463. Min Act: -0.0000

Data Index: 1112137 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 4.8135. Min Range: -4.8135

Max Act: 2.7236. Min Act: -0.0000

Data Index: 775435 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 4.8135. Min Range: -4.8135

Max Act: 2.9919. Min Act: -0.0000

Data Index: 517226 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.0199. Min Act: -0.0000

Data Index: 609366 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 4.8135. Min Range: -4.8135

Max Act: 3.0062. Min Act: -0.0000

Data Index: 1247405 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 4.8135. Min Range: -4.8135

Max Act: 2.8234. Min Act: -0.0000

Data Index: 854206 (C4 (Web Text))

Max Activating Token Index: 923