Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.4935. Min Act: -0.1700

Data Index: 450677 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.4152. Min Act: -0.1700

Data Index: 1104490 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.4308. Min Act: -0.1700

Data Index: 839841 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3838. Min Act: -0.1700

Data Index: 216551 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.4308. Min Act: -0.1700

Data Index: 760340 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1027650 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3995. Min Act: -0.1700

Data Index: 878703 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3995. Min Act: -0.1700

Data Index: 237767 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3524. Min Act: -0.1700

Data Index: 1256470 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3210. Min Act: -0.1700

Data Index: 172083 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1153731 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3995. Min Act: -0.1700

Data Index: 638519 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3995. Min Act: -0.1700

Data Index: 119182 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3838. Min Act: -0.1700

Data Index: 443647 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3681. Min Act: -0.1700

Data Index: 884225 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3524. Min Act: -0.1700

Data Index: 78909 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.4465. Min Act: -0.1700

Data Index: 412602 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3367. Min Act: -0.1700

Data Index: 752394 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3367. Min Act: -0.1700

Data Index: 988629 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 3.4935. Min Range: -3.4935

Max Act: 3.3367. Min Act: -0.1700

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 929