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

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

Neuron 1254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1093. Min Range: -5.1093

Max Act: 5.1093. Min Act: -0.1700

Data Index: 150900 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.9218. Min Act: -0.1700

Data Index: 1287328 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.7968. Min Act: -0.1700

Data Index: 779806 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.7343. Min Act: -0.1700

Data Index: 4511 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.6092. Min Act: -0.1700

Data Index: 399174 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.6092. Min Act: -0.1700

Data Index: 1324522 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5780. Min Act: -0.1700

Data Index: 962187 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5780. Min Act: -0.1700

Data Index: 947891 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5780. Min Act: -0.1700

Data Index: 23675 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5467. Min Act: -0.1700

Data Index: 305620 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5155. Min Act: -0.1700

Data Index: 1025376 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5467. Min Act: -0.1700

Data Index: 1122258 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5155. Min Act: -0.1700

Data Index: 192778 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5155. Min Act: -0.1700

Data Index: 1134914 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.4842. Min Act: -0.1700

Data Index: 739706 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.4842. Min Act: -0.1700

Data Index: 1213885 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.4530. Min Act: -0.1700

Data Index: 288170 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.5155. Min Act: -0.1700

Data Index: 396318 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.4842. Min Act: -0.1700

Data Index: 1250891 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 5.1093. Min Range: -5.1093

Max Act: 4.4530. Min Act: -0.1700

Data Index: 1277540 (C4 (Web Text))

Max Activating Token Index: 773