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

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

Neuron 127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.6949. Min Act: -0.0001

Data Index: 857395 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.6291. Min Act: -0.0001

Data Index: 1016685 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.4775. Min Act: -0.0001

Data Index: 1018825 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.4753. Min Act: -0.0001

Data Index: 839956 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.4305. Min Act: -0.0001

Data Index: 432559 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3969. Min Act: -0.0000

Data Index: 184192 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3833. Min Act: -0.0001

Data Index: 1286521 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3688. Min Act: -0.0001

Data Index: 1172103 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3643. Min Act: -0.0001

Data Index: 1275676 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3564. Min Act: -0.0001

Data Index: 249978 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3072. Min Act: -0.0001

Data Index: 636498 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3560. Min Act: -0.0000

Data Index: 609628 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.3105. Min Act: -0.0001

Data Index: 24410 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.2866. Min Act: -0.0001

Data Index: 714361 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.2536. Min Act: -0.0001

Data Index: 752912 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.2660. Min Act: -0.0001

Data Index: 351077 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.2652. Min Act: -0.0001

Data Index: 41374 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.2529. Min Act: -0.0000

Data Index: 232643 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.2924. Min Act: -0.0001

Data Index: 1132075 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.6949. Min Range: -1.6949

Max Act: 1.2504. Min Act: -0.0001

Data Index: 192034 (C4 (Web Text))

Max Activating Token Index: 234