Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1227 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.0091. Min Range: -7.0091

Max Act: 7.0091. Min Act: -0.1700

Data Index: 39992 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.9466. Min Act: -0.1700

Data Index: 448927 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.9154. Min Act: -0.1700

Data Index: 451977 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.9154. Min Act: -0.1700

Data Index: 556100 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.7904. Min Act: -0.1700

Data Index: 154513 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.7591. Min Act: -0.1700

Data Index: 535485 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.7591. Min Act: -0.1700

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.7591. Min Act: -0.1700

Data Index: 2350 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6654. Min Act: -0.1700

Data Index: 272630 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6341. Min Act: -0.1700

Data Index: 606972 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6654. Min Act: -0.1700

Data Index: 1094090 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6341. Min Act: -0.1700

Data Index: 816522 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6029. Min Act: -0.1700

Data Index: 1129701 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6341. Min Act: -0.1700

Data Index: 65903 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6654. Min Act: -0.1700

Data Index: 689280 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.5716. Min Act: -0.1700

Data Index: 688230 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6029. Min Act: -0.1699

Data Index: 272392 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6029. Min Act: -0.1700

Data Index: 1267635 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.6029. Min Act: -0.1700

Data Index: 295428 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 7.0091. Min Range: -7.0091

Max Act: 6.5716. Min Act: -0.1700

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 353