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

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

Neuron 1877 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: 3.5359. Min Range: -3.5359

Max Act: 3.5359. Min Act: -0.1700

Data Index: 1590082 (Python Code)

Max Activating Token Index: 383

Text #1

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.4353. Min Act: -0.1700

Data Index: 1293761 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.4001. Min Act: -0.1700

Data Index: 988130 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.4065. Min Act: -0.1700

Data Index: 603154 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3976. Min Act: -0.1700

Data Index: 995852 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.4215. Min Act: -0.1700

Data Index: 657394 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3724. Min Act: -0.1700

Data Index: 883642 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3772. Min Act: -0.1700

Data Index: 70542 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3602. Min Act: -0.1700

Data Index: 521347 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3540. Min Act: -0.1700

Data Index: 1050290 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3129. Min Act: -0.1700

Data Index: 469808 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3592. Min Act: -0.1700

Data Index: 1253521 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3456. Min Act: -0.1700

Data Index: 1206958 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3343. Min Act: -0.1700

Data Index: 1112866 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3191. Min Act: -0.1700

Data Index: 581656 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3411. Min Act: -0.1700

Data Index: 568543 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3391. Min Act: -0.1700

Data Index: 319847 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3140. Min Act: -0.1700

Data Index: 1281206 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3251. Min Act: -0.1700

Data Index: 806584 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.5359. Min Range: -3.5359

Max Act: 3.3259. Min Act: -0.1700

Data Index: 1158680 (C4 (Web Text))

Max Activating Token Index: 627