Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3779 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2723. Min Range: -2.2723

Max Act: 2.2723. Min Act: -0.0000

Data Index: 1543262 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.7419. Min Act: -0.0000

Data Index: 901876 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1470876 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.7970. Min Act: -0.0000

Data Index: 1150223 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.8931. Min Act: -0.0000

Data Index: 985731 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.5963. Min Act: -0.0000

Data Index: 773442 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.6967. Min Act: -0.0000

Data Index: 626461 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.5349. Min Act: -0.0000

Data Index: 164563 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.4179. Min Act: -0.0000

Data Index: 1293159 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.4078. Min Act: -0.0000

Data Index: 49160 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.4842. Min Act: -0.0000

Data Index: 1494452 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.4842. Min Act: -0.0000

Data Index: 931042 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.4918. Min Act: -0.0000

Data Index: 745671 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.5018. Min Act: -0.0000

Data Index: 242909 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.2761. Min Act: -0.0000

Data Index: 791878 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.3550. Min Act: -0.0000

Data Index: 1236837 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.2748. Min Act: -0.0000

Data Index: 1233239 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.5203. Min Act: -0.0000

Data Index: 556484 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.3975. Min Act: -0.0000

Data Index: 180917 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 2.2723. Min Range: -2.2723

Max Act: 1.4121. Min Act: -0.0000

Data Index: 252121 (C4 (Web Text))

Max Activating Token Index: 715