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

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

Neuron 285 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: 3.9118. Min Range: -3.9118

Max Act: 3.9118. Min Act: -0.1700

Data Index: 564591 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.8498. Min Act: -0.1700

Data Index: 307280 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.7881. Min Act: -0.1700

Data Index: 403586 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.8189. Min Act: -0.1700

Data Index: 4684 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.8100. Min Act: -0.1700

Data Index: 953170 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.7652. Min Act: -0.1700

Data Index: 93672 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.7052. Min Act: -0.1700

Data Index: 1142604 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.7097. Min Act: -0.1700

Data Index: 881181 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.7249. Min Act: -0.1700

Data Index: 476939 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.7359. Min Act: -0.1700

Data Index: 198363 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6729. Min Act: -0.1700

Data Index: 303684 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6846. Min Act: -0.1700

Data Index: 861151 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1145398 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6466. Min Act: -0.1700

Data Index: 1586491 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6478. Min Act: -0.1700

Data Index: 1635411 (Python Code)

Max Activating Token Index: 229

Text #15

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6376. Min Act: -0.1700

Data Index: 468420 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6573. Min Act: -0.1700

Data Index: 590961 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6818. Min Act: -0.1700

Data Index: 1198306 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6564. Min Act: -0.1700

Data Index: 1324366 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 3.9118. Min Range: -3.9118

Max Act: 3.6363. Min Act: -0.1700

Data Index: 1062282 (C4 (Web Text))

Max Activating Token Index: 937