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

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

Neuron 276 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: 5.7154. Min Range: -5.7154

Max Act: 5.6842. Min Act: -0.1700

Data Index: 1217423 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.7154. Min Act: -0.1700

Data Index: 840767 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.6842. Min Act: -0.1700

Data Index: 502305 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5592. Min Act: -0.1700

Data Index: 108459 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.6842. Min Act: -0.1700

Data Index: 1156914 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.6529. Min Act: -0.1700

Data Index: 1181767 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.6217. Min Act: -0.1700

Data Index: 232902 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5904. Min Act: -0.1700

Data Index: 796518 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.6217. Min Act: -0.1700

Data Index: 919423 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.6842. Min Act: -0.1700

Data Index: 1290586 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.6217. Min Act: -0.1700

Data Index: 1132593 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5279. Min Act: -0.1700

Data Index: 1113925 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5279. Min Act: -0.1700

Data Index: 930723 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5279. Min Act: -0.1700

Data Index: 684468 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5592. Min Act: -0.1700

Data Index: 81588 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5279. Min Act: -0.1700

Data Index: 496465 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5279. Min Act: -0.1700

Data Index: 46544 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5279. Min Act: -0.1700

Data Index: 780484 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.5904. Min Act: -0.1700

Data Index: 987256 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 5.7154. Min Range: -5.7154

Max Act: 5.4967. Min Act: -0.1700

Data Index: 1028293 (C4 (Web Text))

Max Activating Token Index: 565