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

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

Neuron 1447 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: 5.1946. Min Range: -5.1946

Max Act: 5.1946. Min Act: -0.1700

Data Index: 26659 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.1009. Min Act: -0.1700

Data Index: 836623 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.1321. Min Act: -0.1700

Data Index: 67248 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 5.1946. Min Range: -5.1946

Max Act: 4.9446. Min Act: -0.1700

Data Index: 1145782 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 5.1946. Min Range: -5.1946

Max Act: 4.9759. Min Act: -0.1700

Data Index: 456203 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.1009. Min Act: -0.1700

Data Index: 1293449 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0696. Min Act: -0.1700

Data Index: 670417 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0384. Min Act: -0.1700

Data Index: 141754 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0696. Min Act: -0.1700

Data Index: 759705 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0384. Min Act: -0.1700

Data Index: 1313744 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0071. Min Act: -0.1700

Data Index: 475223 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0071. Min Act: -0.1700

Data Index: 16231 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 5.1946. Min Range: -5.1946

Max Act: 4.9759. Min Act: -0.1700

Data Index: 1352551 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 5.1946. Min Range: -5.1946

Max Act: 4.9759. Min Act: -0.1700

Data Index: 923836 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0384. Min Act: -0.1700

Data Index: 418712 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 5.1946. Min Range: -5.1946

Max Act: 4.9446. Min Act: -0.1700

Data Index: 405238 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0071. Min Act: -0.1700

Data Index: 298654 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 5.1946. Min Range: -5.1946

Max Act: 4.9134. Min Act: -0.1700

Data Index: 90563 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 5.1946. Min Range: -5.1946

Max Act: 4.9759. Min Act: -0.1700

Data Index: 269149 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 5.1946. Min Range: -5.1946

Max Act: 5.0071. Min Act: -0.1700

Data Index: 219366 (C4 (Web Text))

Max Activating Token Index: 934