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

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

Neuron 1080 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.4119. Min Act: -0.1700

Data Index: 643590 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.3648. Min Act: -0.1700

Data Index: 388824 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.2549. Min Act: -0.1700

Data Index: 974962 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1211302 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1319996 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1605. Min Act: -0.1700

Data Index: 561398 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1448. Min Act: -0.1700

Data Index: 1387316 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1290. Min Act: -0.1700

Data Index: 1415460 (Python Code)

Max Activating Token Index: 787

Text #8

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1290. Min Act: -0.1700

Data Index: 1458351 (Python Code)

Max Activating Token Index: 934

Text #9

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1290. Min Act: -0.1700

Data Index: 461749 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1133. Min Act: -0.1700

Data Index: 1437041 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1133. Min Act: -0.1700

Data Index: 853318 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.1133. Min Act: -0.1700

Data Index: 1035394 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.0817. Min Act: -0.1700

Data Index: 478570 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.0975. Min Act: -0.1700

Data Index: 1457631 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.0817. Min Act: -0.1700

Data Index: 894437 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.0975. Min Act: -0.1700

Data Index: 1513324 (Python Code)

Max Activating Token Index: 869

Text #17

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.0817. Min Act: -0.1700

Data Index: 187808 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.0660. Min Act: -0.1700

Data Index: 418148 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 3.4119. Min Range: -3.4119

Max Act: 3.0817. Min Act: -0.1700

Data Index: 1153258 (C4 (Web Text))

Max Activating Token Index: 815