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

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

Neuron 1548 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: 4.1249. Min Range: -4.1249

Max Act: 4.1093. Min Act: -0.1700

Data Index: 941248 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.1249. Min Act: -0.1700

Data Index: 413129 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0936. Min Act: -0.1700

Data Index: 90939 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0624. Min Act: -0.1700

Data Index: 630102 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0155. Min Act: -0.1700

Data Index: 384872 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0467. Min Act: -0.1700

Data Index: 1167822 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0311. Min Act: -0.1700

Data Index: 1015734 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0155. Min Act: -0.1700

Data Index: 1319948 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0311. Min Act: -0.1700

Data Index: 1089446 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9530. Min Act: -0.1700

Data Index: 1270216 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 4.1249. Min Range: -4.1249

Max Act: 4.0311. Min Act: -0.1700

Data Index: 368775 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9686. Min Act: -0.1700

Data Index: 852831 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.8435. Min Act: -0.1700

Data Index: 697037 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9686. Min Act: -0.1700

Data Index: 323631 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9373. Min Act: -0.1700

Data Index: 1224191 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.8279. Min Act: -0.1700

Data Index: 946496 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9060. Min Act: -0.1700

Data Index: 55017 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9373. Min Act: -0.1700

Data Index: 1221061 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9842. Min Act: -0.1700

Data Index: 138503 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 4.1249. Min Range: -4.1249

Max Act: 3.9060. Min Act: -0.1700

Data Index: 322559 (C4 (Web Text))

Max Activating Token Index: 83