Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1231 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1636. Min Range: -4.1636

Max Act: 4.1636. Min Act: -0.1700

Data Index: 1273053 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.8675. Min Act: -0.1700

Data Index: 1332253 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.8562. Min Act: -0.1700

Data Index: 167408 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.7974. Min Act: -0.1700

Data Index: 978227 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.8171. Min Act: -0.1700

Data Index: 494905 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.8114. Min Act: -0.1700

Data Index: 1070105 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.7907. Min Act: -0.1700

Data Index: 548620 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.7709. Min Act: -0.1700

Data Index: 987958 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.7231. Min Act: -0.1700

Data Index: 529371 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.7469. Min Act: -0.1700

Data Index: 898855 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.7350. Min Act: -0.1700

Data Index: 607859 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.7227. Min Act: -0.1700

Data Index: 483101 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6672. Min Act: -0.1700

Data Index: 1304732 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6594. Min Act: -0.1700

Data Index: 419324 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6158. Min Act: -0.1700

Data Index: 1070255 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6544. Min Act: -0.1700

Data Index: 943248 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6362. Min Act: -0.1700

Data Index: 727403 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6373. Min Act: -0.1700

Data Index: 584476 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6600. Min Act: -0.1700

Data Index: 662176 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 4.1636. Min Range: -4.1636

Max Act: 3.6174. Min Act: -0.1700

Data Index: 1400748 (Python Code)

Max Activating Token Index: 886