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

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

Neuron 472 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: 8.4073. Min Range: -8.4073

Max Act: 8.4073. Min Act: -0.1699

Data Index: 599348 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.3604. Min Act: -0.1699

Data Index: 220159 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.3448. Min Act: -0.1699

Data Index: 1291678 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.3135. Min Act: -0.1699

Data Index: 1345495 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2979. Min Act: -0.1699

Data Index: 959734 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2979. Min Act: -0.1699

Data Index: 1305600 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2667. Min Act: -0.1699

Data Index: 1090319 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2510. Min Act: -0.1699

Data Index: 299652 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2667. Min Act: -0.1699

Data Index: 568997 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2667. Min Act: -0.1699

Data Index: 639054 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2667. Min Act: -0.1699

Data Index: 653109 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2823. Min Act: -0.1699

Data Index: 946312 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2510. Min Act: -0.1699

Data Index: 503764 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2510. Min Act: -0.1699

Data Index: 811507 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2354. Min Act: -0.1699

Data Index: 1120258 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2823. Min Act: -0.1699

Data Index: 600034 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2354. Min Act: -0.1699

Data Index: 841275 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2667. Min Act: -0.1699

Data Index: 573690 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2510. Min Act: -0.1699

Data Index: 1108214 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 8.4073. Min Range: -8.4073

Max Act: 8.2354. Min Act: -0.1699

Data Index: 1297698 (C4 (Web Text))

Max Activating Token Index: 43