Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 445 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.9064. Min Act: -0.1700

Data Index: 1031165 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7969. Min Act: -0.1700

Data Index: 418420 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7500. Min Act: -0.1700

Data Index: 440892 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7656. Min Act: -0.1700

Data Index: 457057 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7344. Min Act: -0.1700

Data Index: 970824 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7187. Min Act: -0.1700

Data Index: 1044486 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6874. Min Act: -0.1700

Data Index: 800915 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6874. Min Act: -0.1700

Data Index: 104623 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7031. Min Act: -0.1700

Data Index: 1343077 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6718. Min Act: -0.1700

Data Index: 249355 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7031. Min Act: -0.1700

Data Index: 211841 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.7031. Min Act: -0.1700

Data Index: 870783 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6561. Min Act: -0.1700

Data Index: 995316 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6561. Min Act: -0.1700

Data Index: 469167 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6405. Min Act: -0.1700

Data Index: 492680 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.5935. Min Act: -0.1700

Data Index: 1444899 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6248. Min Act: -0.1700

Data Index: 641767 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6092. Min Act: -0.1700

Data Index: 414852 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.6405. Min Act: -0.1700

Data Index: 1143545 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 3.9064. Min Range: -3.9064

Max Act: 3.5935. Min Act: -0.1700

Data Index: 917223 (C4 (Web Text))

Max Activating Token Index: 109