Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1349 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.5046. Min Act: -0.1700

Data Index: 793733 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.4733. Min Act: -0.1700

Data Index: 937253 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.4421. Min Act: -0.1700

Data Index: 1084756 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.3483. Min Act: -0.1700

Data Index: 162776 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.3171. Min Act: -0.1700

Data Index: 1192352 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.3171. Min Act: -0.1700

Data Index: 758804 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.2546. Min Act: -0.1698

Data Index: 1297329 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.3171. Min Act: -0.1700

Data Index: 311823 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.2233. Min Act: -0.1700

Data Index: 673439 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.2233. Min Act: -0.1700

Data Index: 1142575 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.2233. Min Act: -0.1700

Data Index: 357436 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.2233. Min Act: -0.1700

Data Index: 4204 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.2233. Min Act: -0.1700

Data Index: 665504 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.1921. Min Act: -0.1700

Data Index: 426845 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.2233. Min Act: -0.1700

Data Index: 711215 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.1921. Min Act: -0.1700

Data Index: 1201273 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.1608. Min Act: -0.1700

Data Index: 1057130 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.1608. Min Act: -0.1700

Data Index: 407529 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.1296. Min Act: -0.1698

Data Index: 826211 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 5.5046. Min Range: -5.5046

Max Act: 5.1296. Min Act: -0.1700

Data Index: 481331 (C4 (Web Text))

Max Activating Token Index: 862