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

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

Neuron 228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1306977 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4445. Min Act: -0.0001

Data Index: 283249 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1023073 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4164. Min Act: -0.0000

Data Index: 623054 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4377. Min Act: -0.0000

Data Index: 887843 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4175. Min Act: -0.0001

Data Index: 719929 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3870. Min Act: -0.0000

Data Index: 248166 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4010. Min Act: -0.0000

Data Index: 330894 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3981. Min Act: -0.0001

Data Index: 796529 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4086. Min Act: -0.0000

Data Index: 389297 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4253. Min Act: -0.0001

Data Index: 931683 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3972. Min Act: -0.0001

Data Index: 266980 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3950. Min Act: -0.0000

Data Index: 797521 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4097. Min Act: -0.0001

Data Index: 871590 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3995. Min Act: -0.0000

Data Index: 483100 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3942. Min Act: -0.0000

Data Index: 313751 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3746. Min Act: -0.0001

Data Index: 1337850 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1334828 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3865. Min Act: -0.0000

Data Index: 998972 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3958. Min Act: -0.0001

Data Index: 1316575 (C4 (Web Text))

Max Activating Token Index: 165