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

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

Neuron 1284 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0345. Min Range: -7.0345

Max Act: 7.0345. Min Act: -0.1700

Data Index: 454250 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.8157. Min Act: -0.1700

Data Index: 538414 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.5345. Min Act: -0.1700

Data Index: 1597428 (Python Code)

Max Activating Token Index: 709

Text #3

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.5970. Min Act: -0.1700

Data Index: 1344066 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.5970. Min Act: -0.1700

Data Index: 557988 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.5657. Min Act: -0.1700

Data Index: 391694 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.5032. Min Act: -0.1700

Data Index: 749414 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.4720. Min Act: -0.1697

Data Index: 557424 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.4407. Min Act: -0.1700

Data Index: 879444 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.4095. Min Act: -0.1700

Data Index: 834801 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.3470. Min Act: -0.1700

Data Index: 14519 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.3157. Min Act: -0.1700

Data Index: 1282039 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.3782. Min Act: -0.1700

Data Index: 164402 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.3470. Min Act: -0.1700

Data Index: 417131 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.2845. Min Act: -0.1700

Data Index: 990938 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.3470. Min Act: -0.1700

Data Index: 802147 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.3157. Min Act: -0.1700

Data Index: 1281817 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.2845. Min Act: -0.1700

Data Index: 1227762 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.2532. Min Act: -0.1700

Data Index: 694295 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 7.0345. Min Range: -7.0345

Max Act: 6.2532. Min Act: -0.1700

Data Index: 177158 (C4 (Web Text))

Max Activating Token Index: 858