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

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

Neuron 2918 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: 0.4982. Min Range: -0.4982

Max Act: 0.4982. Min Act: -0.0001

Data Index: 464712 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4521. Min Act: -0.0001

Data Index: 162722 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4229. Min Act: -0.0000

Data Index: 938985 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4418. Min Act: -0.0001

Data Index: 982918 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4352. Min Act: -0.0001

Data Index: 292708 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4248. Min Act: -0.0001

Data Index: 505169 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3791. Min Act: -0.0001

Data Index: 13090 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1087069 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3630. Min Act: -0.0001

Data Index: 64410 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3887. Min Act: -0.0001

Data Index: 23276 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3866. Min Act: -0.0001

Data Index: 1261550 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3838. Min Act: -0.0001

Data Index: 1254959 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3858. Min Act: -0.0001

Data Index: 168397 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3457. Min Act: -0.0001

Data Index: 381325 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3543. Min Act: -0.0001

Data Index: 1305117 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3608. Min Act: -0.0001

Data Index: 83360 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3460. Min Act: -0.0001

Data Index: 265774 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3453. Min Act: -0.0001

Data Index: 499669 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3445. Min Act: -0.0001

Data Index: 938455 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1323735 (C4 (Web Text))

Max Activating Token Index: 1021