Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.5488. Min Act: -0.1700

Data Index: 100821 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2676. Min Act: -0.1700

Data Index: 426248 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2676. Min Act: -0.1700

Data Index: 995373 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2051. Min Act: -0.1700

Data Index: 1097116 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2363. Min Act: -0.1700

Data Index: 68351 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2363. Min Act: -0.1700

Data Index: 1341520 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.1738. Min Act: -0.1700

Data Index: 65564 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2363. Min Act: -0.1700

Data Index: 416800 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2988. Min Act: -0.1700

Data Index: 471543 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.1426. Min Act: -0.1700

Data Index: 225537 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.1426. Min Act: -0.1700

Data Index: 310970 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.1426. Min Act: -0.1700

Data Index: 541709 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2363. Min Act: -0.1700

Data Index: 1194517 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2051. Min Act: -0.1700

Data Index: 614042 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.2051. Min Act: -0.1700

Data Index: 937130 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.0801. Min Act: -0.1700

Data Index: 427949 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.1113. Min Act: -0.1700

Data Index: 480757 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.0488. Min Act: -0.1700

Data Index: 1121541 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.0488. Min Act: -0.1700

Data Index: 868583 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 5.5488. Min Range: -5.5488

Max Act: 5.0801. Min Act: -0.1700

Data Index: 1038630 (C4 (Web Text))

Max Activating Token Index: 689