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

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

Neuron 1647 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: 4.0793. Min Range: -4.0793

Max Act: 4.0793. Min Act: -0.1700

Data Index: 539312 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9699. Min Act: -0.1700

Data Index: 32289 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9542. Min Act: -0.1698

Data Index: 413890 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9699. Min Act: -0.1700

Data Index: 248555 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9386. Min Act: -0.1700

Data Index: 987856 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9230. Min Act: -0.1700

Data Index: 585320 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9386. Min Act: -0.1700

Data Index: 465394 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9073. Min Act: -0.1700

Data Index: 1091757 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.9230. Min Act: -0.1699

Data Index: 557292 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8761. Min Act: -0.1700

Data Index: 119379 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8917. Min Act: -0.1700

Data Index: 1259656 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8448. Min Act: -0.1700

Data Index: 1030605 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8917. Min Act: -0.1700

Data Index: 404000 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8448. Min Act: -0.1700

Data Index: 443022 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8448. Min Act: -0.1700

Data Index: 55986 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8604. Min Act: -0.1700

Data Index: 1309685 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8291. Min Act: -0.1696

Data Index: 745479 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8291. Min Act: -0.1700

Data Index: 1118039 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8291. Min Act: -0.1700

Data Index: 861830 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 4.0793. Min Range: -4.0793

Max Act: 3.8135. Min Act: -0.1699

Data Index: 744432 (C4 (Web Text))

Max Activating Token Index: 385