Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1349 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.4007. Min Act: -0.0001

Data Index: 353994 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3758. Min Act: -0.0001

Data Index: 618761 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3622. Min Act: -0.0001

Data Index: 636809 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3470. Min Act: -0.0001

Data Index: 336435 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3563. Min Act: -0.0001

Data Index: 941423 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3409. Min Act: -0.0001

Data Index: 534825 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3195. Min Act: -0.0001

Data Index: 407155 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3326. Min Act: -0.0001

Data Index: 21510 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3191. Min Act: -0.0001

Data Index: 874088 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2995. Min Act: -0.0001

Data Index: 800227 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3321. Min Act: -0.0001

Data Index: 307531 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3160. Min Act: -0.0001

Data Index: 174819 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3190. Min Act: -0.0001

Data Index: 900850 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3130. Min Act: -0.0001

Data Index: 134181 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3250. Min Act: -0.0001

Data Index: 1063942 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1044279 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3338. Min Act: -0.0001

Data Index: 811244 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3151. Min Act: -0.0001

Data Index: 235136 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.3196. Min Act: -0.0001

Data Index: 952090 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.4007. Min Range: -0.4007

Max Act: 0.2962. Min Act: -0.0001

Data Index: 862307 (C4 (Web Text))

Max Activating Token Index: 997