Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1847 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.3461. Min Act: -0.1700

Data Index: 575547 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.2937. Min Act: -0.1700

Data Index: 1085866 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.2086. Min Act: -0.1700

Data Index: 621195 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.2557. Min Act: -0.1700

Data Index: 1137354 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1905. Min Act: -0.1700

Data Index: 997284 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.2198. Min Act: -0.1700

Data Index: 228587 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1901. Min Act: -0.1700

Data Index: 925161 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1970. Min Act: -0.1700

Data Index: 684131 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1601. Min Act: -0.1700

Data Index: 226342 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1680. Min Act: -0.1700

Data Index: 150345 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1578. Min Act: -0.1700

Data Index: 483143 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1587. Min Act: -0.1700

Data Index: 1083627 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1585. Min Act: -0.1700

Data Index: 188481 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1493. Min Act: -0.1700

Data Index: 1247883 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1065. Min Act: -0.1700

Data Index: 79868 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1270. Min Act: -0.1700

Data Index: 91710 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1116. Min Act: -0.1700

Data Index: 698824 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1198. Min Act: -0.1700

Data Index: 140992 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1076. Min Act: -0.1700

Data Index: 866054 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 3.3461. Min Range: -3.3461

Max Act: 3.1087. Min Act: -0.1700

Data Index: 151891 (C4 (Web Text))

Max Activating Token Index: 67