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

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

Neuron 3517 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1240164 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3438. Min Act: -0.0000

Data Index: 162637 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3656. Min Act: -0.0000

Data Index: 991328 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3219. Min Act: -0.0000

Data Index: 317071 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3142. Min Act: -0.0000

Data Index: 34052 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1171848 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1059596 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3278. Min Act: -0.0000

Data Index: 879036 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3074. Min Act: -0.0000

Data Index: 61364 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3014. Min Act: -0.0000

Data Index: 385048 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3016. Min Act: -0.0000

Data Index: 553250 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.2937. Min Act: -0.0000

Data Index: 446281 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.2942. Min Act: -0.0000

Data Index: 633381 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1301394 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3091. Min Act: -0.0000

Data Index: 873542 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.2695. Min Act: -0.0000

Data Index: 537678 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.2865. Min Act: -0.0000

Data Index: 688685 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.2956. Min Act: -0.0000

Data Index: 438329 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.2804. Min Act: -0.0000

Data Index: 798840 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.2915. Min Act: -0.0000

Data Index: 695858 (C4 (Web Text))

Max Activating Token Index: 406