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

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

Neuron 1429 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: 0.5471. Min Range: -0.5471

Max Act: 0.5471. Min Act: -0.0001

Data Index: 380819 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4880. Min Act: -0.0000

Data Index: 913222 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4531. Min Act: -0.0001

Data Index: 906848 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4242. Min Act: -0.0000

Data Index: 824543 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4202. Min Act: -0.0001

Data Index: 1227103 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4192. Min Act: -0.0001

Data Index: 1238833 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1313881 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3994. Min Act: -0.0000

Data Index: 974497 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3924. Min Act: -0.0000

Data Index: 168045 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3881. Min Act: -0.0001

Data Index: 1128241 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3714. Min Act: -0.0000

Data Index: 652284 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3762. Min Act: -0.0000

Data Index: 801200 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3602. Min Act: -0.0000

Data Index: 318162 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3705. Min Act: -0.0000

Data Index: 521508 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3585. Min Act: -0.0000

Data Index: 140359 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3682. Min Act: -0.0001

Data Index: 421007 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3659. Min Act: -0.0000

Data Index: 698589 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3649. Min Act: -0.0000

Data Index: 505803 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3528. Min Act: -0.0001

Data Index: 403022 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3726. Min Act: -0.0000

Data Index: 935327 (C4 (Web Text))

Max Activating Token Index: 361