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

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

Neuron 1054 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: 3.7260. Min Range: -3.7260

Max Act: 3.7133. Min Act: -0.1700

Data Index: 902753 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.7260. Min Act: -0.1700

Data Index: 1388250 (Python Code)

Max Activating Token Index: 180

Text #2

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.5075. Min Act: -0.1700

Data Index: 1329114 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4459. Min Act: -0.1700

Data Index: 486623 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4692. Min Act: -0.1700

Data Index: 1594288 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4257. Min Act: -0.1700

Data Index: 319678 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4323. Min Act: -0.1700

Data Index: 193045 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3820. Min Act: -0.1700

Data Index: 722947 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.4039. Min Act: -0.1700

Data Index: 118527 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3864. Min Act: -0.1700

Data Index: 1523247 (Python Code)

Max Activating Token Index: 679

Text #10

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3815. Min Act: -0.1700

Data Index: 240002 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3908. Min Act: -0.1700

Data Index: 332059 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3901. Min Act: -0.1700

Data Index: 1637197 (Python Code)

Max Activating Token Index: 633

Text #13

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3763. Min Act: -0.1700

Data Index: 1350382 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3497. Min Act: -0.1700

Data Index: 1551332 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3612. Min Act: -0.1700

Data Index: 724996 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3380. Min Act: -0.1700

Data Index: 557303 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3569. Min Act: -0.1700

Data Index: 1358291 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3285. Min Act: -0.1700

Data Index: 1514811 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 3.7260. Min Range: -3.7260

Max Act: 3.3200. Min Act: -0.1700

Data Index: 378132 (C4 (Web Text))

Max Activating Token Index: 783