Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1165 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.9510. Min Act: -0.1700

Data Index: 773562 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.7010. Min Act: -0.1700

Data Index: 659263 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.6385. Min Act: -0.1700

Data Index: 645263 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.7322. Min Act: -0.1700

Data Index: 639021 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.5760. Min Act: -0.1700

Data Index: 1136019 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.5135. Min Act: -0.1700

Data Index: 834267 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.5135. Min Act: -0.1700

Data Index: 71216 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.5135. Min Act: -0.1700

Data Index: 414480 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.4822. Min Act: -0.1700

Data Index: 1350530 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.4510. Min Act: -0.1700

Data Index: 610017 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.4197. Min Act: -0.1700

Data Index: 618444 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.4197. Min Act: -0.1700

Data Index: 970101 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.4510. Min Act: -0.1700

Data Index: 123834 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.4197. Min Act: -0.1700

Data Index: 1096373 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.3885. Min Act: -0.1700

Data Index: 299446 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.4510. Min Act: -0.1700

Data Index: 991805 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.3885. Min Act: -0.1700

Data Index: 120517 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.3885. Min Act: -0.1700

Data Index: 411544 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.3572. Min Act: -0.1700

Data Index: 1107144 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 5.9510. Min Range: -5.9510

Max Act: 5.3572. Min Act: -0.1700

Data Index: 457597 (C4 (Web Text))

Max Activating Token Index: 610