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

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

Neuron 1477 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.6464. Min Act: -0.1700

Data Index: 467667 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.6150. Min Act: -0.1700

Data Index: 278208 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.5837. Min Act: -0.1700

Data Index: 595622 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.5837. Min Act: -0.1700

Data Index: 163828 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.6150. Min Act: -0.1700

Data Index: 9773 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.5211. Min Act: -0.1700

Data Index: 1169867 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.5367. Min Act: -0.1700

Data Index: 886143 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.5367. Min Act: -0.1700

Data Index: 328766 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.5211. Min Act: -0.1700

Data Index: 1168424 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4897. Min Act: -0.1700

Data Index: 328614 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4427. Min Act: -0.1700

Data Index: 384872 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4741. Min Act: -0.1700

Data Index: 1140782 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4897. Min Act: -0.1700

Data Index: 930815 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4897. Min Act: -0.1700

Data Index: 422736 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4427. Min Act: -0.1700

Data Index: 135390 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4114. Min Act: -0.1700

Data Index: 954870 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4741. Min Act: -0.1700

Data Index: 161663 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4427. Min Act: -0.1700

Data Index: 833055 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4270. Min Act: -0.1700

Data Index: 236183 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 3.6464. Min Range: -3.6464

Max Act: 3.4270. Min Act: -0.1700

Data Index: 471911 (C4 (Web Text))

Max Activating Token Index: 796