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

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

Neuron 347 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: 3.5347. Min Range: -3.5347

Max Act: 3.5299. Min Act: -0.1698

Data Index: 1205261 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.5295. Min Act: -0.1699

Data Index: 301431 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.5347. Min Act: -0.1697

Data Index: 282675 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4842. Min Act: -0.1700

Data Index: 1247640 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4475. Min Act: -0.1693

Data Index: 156763 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4279. Min Act: -0.1700

Data Index: 1265158 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4419. Min Act: -0.1700

Data Index: 1053719 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4243. Min Act: -0.1698

Data Index: 687742 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4327. Min Act: -0.1700

Data Index: 108952 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4266. Min Act: -0.1696

Data Index: 645126 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3857. Min Act: -0.1699

Data Index: 38767 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3791. Min Act: -0.1700

Data Index: 39605 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.4164. Min Act: -0.1700

Data Index: 607281 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3980. Min Act: -0.1700

Data Index: 881824 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3952. Min Act: -0.1700

Data Index: 886808 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3584. Min Act: -0.1699

Data Index: 818069 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3628. Min Act: -0.1700

Data Index: 51359 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3539. Min Act: -0.1700

Data Index: 643127 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3518. Min Act: -0.1699

Data Index: 583746 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 3.5347. Min Range: -3.5347

Max Act: 3.3283. Min Act: -0.1700

Data Index: 194568 (C4 (Web Text))

Max Activating Token Index: 569