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

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

Neuron 1458 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: 3.9159. Min Range: -3.9159

Max Act: 3.9159. Min Act: -0.1700

Data Index: 706366 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.6030. Min Act: -0.1700

Data Index: 870058 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.6030. Min Act: -0.1700

Data Index: 36994 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.6030. Min Act: -0.1700

Data Index: 744540 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5717. Min Act: -0.1700

Data Index: 356444 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5717. Min Act: -0.1700

Data Index: 782763 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5404. Min Act: -0.1700

Data Index: 171091 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5404. Min Act: -0.1700

Data Index: 100847 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4777. Min Act: -0.1700

Data Index: 1312658 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4777. Min Act: -0.1700

Data Index: 1350956 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4464. Min Act: -0.1700

Data Index: 886364 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5404. Min Act: -0.1700

Data Index: 660102 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5091. Min Act: -0.1700

Data Index: 685652 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5091. Min Act: -0.1700

Data Index: 601297 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4777. Min Act: -0.1700

Data Index: 575398 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4464. Min Act: -0.1700

Data Index: 727877 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4777. Min Act: -0.1700

Data Index: 759303 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.5404. Min Act: -0.1700

Data Index: 955907 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4777. Min Act: -0.1700

Data Index: 1121213 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 3.9159. Min Range: -3.9159

Max Act: 3.4777. Min Act: -0.1700

Data Index: 1196248 (C4 (Web Text))

Max Activating Token Index: 618