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

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

Neuron 1896 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: 5.7873. Min Range: -5.7873

Max Act: 5.7873. Min Act: -0.1700

Data Index: 81615 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.7560. Min Act: -0.1700

Data Index: 515117 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.7560. Min Act: -0.1700

Data Index: 807353 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.6935. Min Act: -0.1700

Data Index: 1279034 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.5373. Min Act: -0.1700

Data Index: 187286 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.5060. Min Act: -0.1700

Data Index: 126931 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.5060. Min Act: -0.1700

Data Index: 1163651 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4748. Min Act: -0.1700

Data Index: 1297089 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4748. Min Act: -0.1700

Data Index: 1252548 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4748. Min Act: -0.1700

Data Index: 236437 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.3810. Min Act: -0.1700

Data Index: 633762 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1101168 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4435. Min Act: -0.1700

Data Index: 99112 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4123. Min Act: -0.1700

Data Index: 6193 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4435. Min Act: -0.1699

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4123. Min Act: -0.1700

Data Index: 1088464 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.4435. Min Act: -0.1700

Data Index: 224443 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.3498. Min Act: -0.1700

Data Index: 575387 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.3810. Min Act: -0.1700

Data Index: 625141 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 5.7873. Min Range: -5.7873

Max Act: 5.3810. Min Act: -0.1700

Data Index: 1355113 (C4 (Web Text))

Max Activating Token Index: 308