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

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

Neuron 857 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: 4.7072. Min Range: -4.7072

Max Act: 4.7017. Min Act: -0.1700

Data Index: 131641 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.7007. Min Act: -0.1700

Data Index: 1175039 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6965. Min Act: -0.1700

Data Index: 155128 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6800. Min Act: -0.1700

Data Index: 1121865 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.7004. Min Act: -0.1700

Data Index: 924732 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6965. Min Act: -0.1700

Data Index: 693269 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.7072. Min Act: -0.1700

Data Index: 623372 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6670. Min Act: -0.1700

Data Index: 253587 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6648. Min Act: -0.1700

Data Index: 184191 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6796. Min Act: -0.1700

Data Index: 483973 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6723. Min Act: -0.1700

Data Index: 373867 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6463. Min Act: -0.1700

Data Index: 776332 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6665. Min Act: -0.1700

Data Index: 805985 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6645. Min Act: -0.1700

Data Index: 683627 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6408. Min Act: -0.1700

Data Index: 334981 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6312. Min Act: -0.1700

Data Index: 416631 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6123. Min Act: -0.1700

Data Index: 402924 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6399. Min Act: -0.1700

Data Index: 566339 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6276. Min Act: -0.1700

Data Index: 313930 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 4.7072. Min Range: -4.7072

Max Act: 4.6394. Min Act: -0.1700

Data Index: 240066 (C4 (Web Text))

Max Activating Token Index: 67