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

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

Neuron 66 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: 0.3845. Min Range: -0.3845

Max Act: 0.3194. Min Act: -0.0001

Data Index: 345084 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3104. Min Act: -0.0001

Data Index: 804426 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3251. Min Act: -0.0001

Data Index: 451691 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3845. Min Act: -0.0001

Data Index: 314139 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3503. Min Act: -0.0001

Data Index: 950397 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3479. Min Act: -0.0001

Data Index: 159728 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3486. Min Act: -0.0001

Data Index: 109256 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3259. Min Act: -0.0002

Data Index: 419857 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3054. Min Act: -0.0001

Data Index: 1208584 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3246. Min Act: -0.0001

Data Index: 318419 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3318. Min Act: -0.0002

Data Index: 131410 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3076. Min Act: -0.0001

Data Index: 571053 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3072. Min Act: -0.0001

Data Index: 106157 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3294. Min Act: -0.0001

Data Index: 158562 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3100. Min Act: -0.0001

Data Index: 642889 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.2980. Min Act: -0.0001

Data Index: 923813 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3046. Min Act: -0.0002

Data Index: 656212 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3301. Min Act: -0.0001

Data Index: 1164622 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.3008. Min Act: -0.0001

Data Index: 418484 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.3845. Min Range: -0.3845

Max Act: 0.2943. Min Act: -0.0002

Data Index: 1091821 (C4 (Web Text))

Max Activating Token Index: 211