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

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

Neuron 1822 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: 3.6224. Min Range: -3.6224

Max Act: 3.6224. Min Act: -0.1700

Data Index: 528112 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4273. Min Act: -0.1700

Data Index: 1194376 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4058. Min Act: -0.1700

Data Index: 1145143 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4114. Min Act: -0.1700

Data Index: 38 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4104. Min Act: -0.1700

Data Index: 513902 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4118. Min Act: -0.1700

Data Index: 276612 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3839. Min Act: -0.1700

Data Index: 1299289 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3752. Min Act: -0.1700

Data Index: 359189 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3667. Min Act: -0.1700

Data Index: 541967 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3636. Min Act: -0.1700

Data Index: 463811 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3350. Min Act: -0.1700

Data Index: 347959 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3458. Min Act: -0.1700

Data Index: 145448 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3331. Min Act: -0.1700

Data Index: 1187282 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3368. Min Act: -0.1700

Data Index: 848376 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.2850. Min Act: -0.1700

Data Index: 693791 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3095. Min Act: -0.1700

Data Index: 677022 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.3025. Min Act: -0.1700

Data Index: 737106 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.2913. Min Act: -0.1700

Data Index: 738761 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.2697. Min Act: -0.1700

Data Index: 879393 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.2863. Min Act: -0.1700

Data Index: 595570 (C4 (Web Text))

Max Activating Token Index: 17