Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1236 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.2585. Min Act: -0.1700

Data Index: 1185609 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.2585. Min Act: -0.1700

Data Index: 289540 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.2270. Min Act: -0.1700

Data Index: 1092720 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.2270. Min Act: -0.1700

Data Index: 670190 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.2113. Min Act: -0.1700

Data Index: 1171010 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.2113. Min Act: -0.1700

Data Index: 729344 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1956. Min Act: -0.1700

Data Index: 823682 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1798. Min Act: -0.1700

Data Index: 1072754 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1641. Min Act: -0.1700

Data Index: 1259069 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1484. Min Act: -0.1700

Data Index: 1053653 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1168. Min Act: -0.1700

Data Index: 1175417 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1484. Min Act: -0.1700

Data Index: 341348 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1484. Min Act: -0.1700

Data Index: 1244187 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1484. Min Act: -0.1700

Data Index: 865915 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1484. Min Act: -0.1700

Data Index: 123944 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1641. Min Act: -0.1700

Data Index: 383080 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1484. Min Act: -0.1700

Data Index: 562931 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1326. Min Act: -0.1700

Data Index: 399892 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1168. Min Act: -0.1700

Data Index: 1063268 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.1326. Min Act: -0.1700

Data Index: 851020 (C4 (Web Text))

Max Activating Token Index: 292