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

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

Neuron 2274 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.3951. Min Act: -0.0001

Data Index: 198600 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.4457. Min Act: -0.0002

Data Index: 567723 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.4380. Min Act: -0.0001

Data Index: 580363 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.3907. Min Act: -0.0001

Data Index: 205872 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.4083. Min Act: -0.0001

Data Index: 106502 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.3408. Min Act: -0.0001

Data Index: 894920 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.3902. Min Act: -0.0001

Data Index: 581265 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2843. Min Act: -0.0001

Data Index: 451689 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2827. Min Act: -0.0001

Data Index: 719914 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2458. Min Act: -0.0001

Data Index: 1173147 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2946. Min Act: -0.0001

Data Index: 674380 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2120. Min Act: -0.0001

Data Index: 1312980 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2613. Min Act: -0.0002

Data Index: 510514 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2937. Min Act: -0.0001

Data Index: 70010 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2890. Min Act: -0.0001

Data Index: 177479 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2379. Min Act: -0.0001

Data Index: 114997 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.1998. Min Act: -0.0001

Data Index: 370653 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.1596. Min Act: -0.0001

Data Index: 490988 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.1979. Min Act: -0.0001

Data Index: 1011213 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 1.4457. Min Range: -1.4457

Max Act: 1.2186. Min Act: -0.0002

Data Index: 69084 (C4 (Web Text))

Max Activating Token Index: 400