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

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

Neuron 1041 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: 3.1374. Min Range: -3.1374

Max Act: 3.1374. Min Act: -0.1700

Data Index: 1056594 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0947. Min Act: -0.1698

Data Index: 613670 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0938. Min Act: -0.1700

Data Index: 1267759 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0790. Min Act: -0.1700

Data Index: 731099 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0569. Min Act: -0.1700

Data Index: 807977 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0354. Min Act: -0.1700

Data Index: 365358 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0279. Min Act: -0.1700

Data Index: 1162643 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0331. Min Act: -0.1700

Data Index: 864307 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 3.1374. Min Range: -3.1374

Max Act: 3.0134. Min Act: -0.1700

Data Index: 806162 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9908. Min Act: -0.1699

Data Index: 723022 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9938. Min Act: -0.1700

Data Index: 601342 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9812. Min Act: -0.1700

Data Index: 1250194 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9805. Min Act: -0.1700

Data Index: 628414 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9550. Min Act: -0.1700

Data Index: 216998 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9630. Min Act: -0.1700

Data Index: 98942 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9668. Min Act: -0.1699

Data Index: 1100447 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9594. Min Act: -0.1700

Data Index: 52289 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9479. Min Act: -0.1700

Data Index: 131577 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9573. Min Act: -0.1700

Data Index: 904930 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 3.1374. Min Range: -3.1374

Max Act: 2.9548. Min Act: -0.1700

Data Index: 455746 (C4 (Web Text))

Max Activating Token Index: 275