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

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

Neuron 439 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: 0.6897. Min Range: -0.6897

Max Act: 0.6897. Min Act: -0.0001

Data Index: 1540608 (Python Code)

Max Activating Token Index: 388

Text #1

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6172. Min Act: -0.0001

Data Index: 1365347 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6355. Min Act: -0.0001

Data Index: 1388646 (Python Code)

Max Activating Token Index: 253

Text #3

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5678. Min Act: -0.0001

Data Index: 1651585 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5252. Min Act: -0.0000

Data Index: 910748 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1651707 (Python Code)

Max Activating Token Index: 723

Text #6

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5470. Min Act: -0.0000

Data Index: 975218 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5297. Min Act: -0.0001

Data Index: 1540128 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5008. Min Act: -0.0001

Data Index: 1631470 (Python Code)

Max Activating Token Index: 586

Text #9

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5067. Min Act: -0.0001

Data Index: 1612967 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4988. Min Act: -0.0001

Data Index: 1567143 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1376337 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4731. Min Act: -0.0001

Data Index: 1452716 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4638. Min Act: -0.0001

Data Index: 1461773 (Python Code)

Max Activating Token Index: 995

Text #14

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1616822 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4972. Min Act: -0.0001

Data Index: 1568864 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1548971 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4449. Min Act: -0.0001

Data Index: 1463577 (Python Code)

Max Activating Token Index: 685

Text #18

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4867. Min Act: -0.0001

Data Index: 1403092 (Python Code)

Max Activating Token Index: 621

Text #19

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4711. Min Act: -0.0001

Data Index: 1510504 (Python Code)

Max Activating Token Index: 235