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

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

Neuron 2480 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.8396. Min Act: -0.0000

Data Index: 1159756 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6936. Min Act: -0.0000

Data Index: 331155 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6607. Min Act: -0.0000

Data Index: 170458 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6737. Min Act: -0.0001

Data Index: 667881 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6545. Min Act: -0.0000

Data Index: 349379 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6095. Min Act: -0.0000

Data Index: 979098 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6109. Min Act: -0.0000

Data Index: 347303 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5723. Min Act: -0.0001

Data Index: 700336 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6257. Min Act: -0.0001

Data Index: 1236461 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6034. Min Act: -0.0001

Data Index: 1215240 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5940. Min Act: -0.0000

Data Index: 831116 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5933. Min Act: -0.0001

Data Index: 566090 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5793. Min Act: -0.0001

Data Index: 423347 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5543. Min Act: -0.0000

Data Index: 944531 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5717. Min Act: -0.0001

Data Index: 1301469 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5843. Min Act: -0.0001

Data Index: 252628 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1089522 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1096064 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5767. Min Act: -0.0000

Data Index: 421543 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5542. Min Act: 0.0001

Data Index: 171709 (C4 (Web Text))

Max Activating Token Index: 555