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

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

Neuron 1511 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 27.7276. Min Range: -27.7276

Max Act: 27.7276. Min Act: -0.1520

Data Index: 1168463 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 27.7276. Min Range: -27.7276

Max Act: 27.6026. Min Act: -0.0359

Data Index: 782125 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 27.7276. Min Range: -27.7276

Max Act: 27.2276. Min Act: -0.0014

Data Index: 35449 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 27.7276. Min Range: -27.7276

Max Act: 27.1026. Min Act: -0.1612

Data Index: 293575 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.9776. Min Act: -0.0154

Data Index: 810501 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.8526. Min Act: -0.1459

Data Index: 1349216 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.9776. Min Act: -0.0338

Data Index: 972016 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.9776. Min Act: -0.0788

Data Index: 1148437 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.7276. Min Act: -0.1581

Data Index: 1268803 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.9776. Min Act: -0.0513

Data Index: 455786 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.9776. Min Act: -0.0068

Data Index: 150923 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 27.7276. Min Range: -27.7276

Max Act: 27.1026. Min Act: -0.0034

Data Index: 514072 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.8526. Min Act: -0.1312

Data Index: 604460 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.8526. Min Act: -0.1463

Data Index: 681158 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.7276. Min Act: -0.0060

Data Index: 248719 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.7276. Min Act: -0.1488

Data Index: 889697 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.7276. Min Act: -0.1036

Data Index: 1165706 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.8526. Min Act: -0.0140

Data Index: 1312706 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.8526. Min Act: -0.0243

Data Index: 1328164 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 27.7276. Min Range: -27.7276

Max Act: 26.7276. Min Act: -0.0126

Data Index: 905013 (C4 (Web Text))

Max Activating Token Index: 1015