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

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

Neuron 1549 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: 3.3688. Min Range: -3.3688

Max Act: 3.3688. Min Act: -0.1700

Data Index: 863840 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.3532. Min Act: -0.1700

Data Index: 515927 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2589. Min Act: -0.1700

Data Index: 1008275 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2432. Min Act: -0.1700

Data Index: 301510 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2275. Min Act: -0.1700

Data Index: 78074 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.2118. Min Act: -0.1700

Data Index: 516495 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1960. Min Act: -0.1700

Data Index: 122985 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1015. Min Act: -0.1700

Data Index: 1013386 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1330. Min Act: -0.1700

Data Index: 672842 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1015. Min Act: -0.1700

Data Index: 470303 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1330. Min Act: -0.1700

Data Index: 663602 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1173. Min Act: -0.1700

Data Index: 318541 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1015. Min Act: -0.1700

Data Index: 673512 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1173. Min Act: -0.1700

Data Index: 944532 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.0858. Min Act: -0.1700

Data Index: 1347743 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1173. Min Act: -0.1700

Data Index: 147245 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.0700. Min Act: -0.1700

Data Index: 1260747 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.0858. Min Act: -0.1700

Data Index: 50439 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.0384. Min Act: -0.1700

Data Index: 947599 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 3.3688. Min Range: -3.3688

Max Act: 3.1015. Min Act: -0.1700

Data Index: 997191 (C4 (Web Text))

Max Activating Token Index: 402