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

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

Neuron 1697 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: 3.4101. Min Range: -3.4101

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1294114 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.3305. Min Act: -0.1697

Data Index: 1343964 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2968. Min Act: -0.1698

Data Index: 735889 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2854. Min Act: -0.1700

Data Index: 764380 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2494. Min Act: -0.1700

Data Index: 1150702 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2435. Min Act: -0.1700

Data Index: 1029260 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2446. Min Act: -0.1700

Data Index: 254634 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2327. Min Act: -0.1700

Data Index: 226066 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2244. Min Act: -0.1700

Data Index: 609682 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2084. Min Act: -0.1700

Data Index: 649980 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2140. Min Act: -0.1700

Data Index: 385264 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2053. Min Act: -0.1700

Data Index: 1293618 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2025. Min Act: -0.1700

Data Index: 1307537 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.2124. Min Act: -0.1700

Data Index: 1249675 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.1871. Min Act: -0.1700

Data Index: 204137 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.1930. Min Act: -0.1700

Data Index: 8896 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.1841. Min Act: -0.1700

Data Index: 467539 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.1978. Min Act: -0.1700

Data Index: 512979 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.1857. Min Act: -0.1700

Data Index: 134212 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 3.4101. Min Range: -3.4101

Max Act: 3.1900. Min Act: -0.1700

Data Index: 1155908 (C4 (Web Text))

Max Activating Token Index: 41