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

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

Neuron 622 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.6489. Min Act: -0.0001

Data Index: 988638 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.5594. Min Act: -0.0001

Data Index: 829988 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4851. Min Act: -0.0001

Data Index: 412822 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4829. Min Act: -0.0001

Data Index: 72722 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4754. Min Act: -0.0001

Data Index: 925864 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4581. Min Act: -0.0001

Data Index: 285854 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4436. Min Act: -0.0001

Data Index: 292930 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4439. Min Act: -0.0001

Data Index: 13380 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4263. Min Act: -0.0001

Data Index: 1061404 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1328172 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4118. Min Act: -0.0001

Data Index: 251606 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4171. Min Act: -0.0001

Data Index: 945183 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1328835 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.3817. Min Act: -0.0001

Data Index: 812678 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.3597. Min Act: -0.0001

Data Index: 1023868 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.3709. Min Act: -0.0001

Data Index: 51784 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.3514. Min Act: -0.0001

Data Index: 356563 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.4082. Min Act: -0.0001

Data Index: 312937 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.3582. Min Act: -0.0001

Data Index: 303387 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.6489. Min Range: -0.6489

Max Act: 0.3658. Min Act: -0.0001

Data Index: 1224951 (C4 (Web Text))

Max Activating Token Index: 404