Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1755 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2469. Min Range: -5.2469

Max Act: 5.2469. Min Act: -0.1700

Data Index: 1613859 (Python Code)

Max Activating Token Index: 437

Text #1

Max Range: 5.2469. Min Range: -5.2469

Max Act: 5.2469. Min Act: -0.1700

Data Index: 1565011 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 5.2469. Min Range: -5.2469

Max Act: 5.1844. Min Act: -0.1700

Data Index: 587964 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 5.2469. Min Range: -5.2469

Max Act: 5.1219. Min Act: -0.1700

Data Index: 1482703 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 5.2469. Min Range: -5.2469

Max Act: 5.0281. Min Act: -0.1700

Data Index: 1544187 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.9344. Min Act: -0.1700

Data Index: 1436257 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.8406. Min Act: -0.1700

Data Index: 1521065 (Python Code)

Max Activating Token Index: 417

Text #7

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.8719. Min Act: -0.1700

Data Index: 1163568 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.8094. Min Act: -0.1700

Data Index: 1553683 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.8406. Min Act: -0.1700

Data Index: 1618737 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.7469. Min Act: -0.1700

Data Index: 1646727 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.6843. Min Act: -0.1700

Data Index: 1455475 (Python Code)

Max Activating Token Index: 631

Text #12

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.7156. Min Act: -0.1700

Data Index: 1638185 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.6218. Min Act: -0.1700

Data Index: 1396687 (Python Code)

Max Activating Token Index: 321

Text #14

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.6218. Min Act: -0.1700

Data Index: 1397423 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.6218. Min Act: -0.1700

Data Index: 1512393 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.5906. Min Act: -0.1700

Data Index: 1657062 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.5906. Min Act: -0.1700

Data Index: 1391310 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.5593. Min Act: -0.1700

Data Index: 1373928 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 5.2469. Min Range: -5.2469

Max Act: 4.5906. Min Act: -0.1700

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 707