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

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

Neuron 835 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: 1.0146. Min Range: -1.0146

Max Act: 1.0146. Min Act: -0.0001

Data Index: 1247756 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9953. Min Act: -0.0001

Data Index: 521262 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9687. Min Act: -0.0001

Data Index: 264700 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8761. Min Act: -0.0001

Data Index: 728888 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8162. Min Act: -0.0001

Data Index: 318396 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.9371. Min Act: -0.0001

Data Index: 862207 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8760. Min Act: -0.0001

Data Index: 838479 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8726. Min Act: -0.0001

Data Index: 72700 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7600. Min Act: -0.0001

Data Index: 980653 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8516. Min Act: -0.0001

Data Index: 1356986 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8048. Min Act: -0.0001

Data Index: 677523 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7482. Min Act: -0.0001

Data Index: 781988 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7613. Min Act: -0.0001

Data Index: 310151 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7997. Min Act: -0.0001

Data Index: 984613 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7982. Min Act: -0.0001

Data Index: 517602 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7497. Min Act: -0.0001

Data Index: 87337 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7335. Min Act: -0.0001

Data Index: 605888 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.8145. Min Act: -0.0001

Data Index: 776020 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7347. Min Act: -0.0001

Data Index: 508287 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 1.0146. Min Range: -1.0146

Max Act: 0.7564. Min Act: -0.0001

Data Index: 630585 (C4 (Web Text))

Max Activating Token Index: 832