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

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

Neuron 1425 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: 7.6448. Min Range: -7.6448

Max Act: 7.6448. Min Act: -0.1700

Data Index: 177020 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.5510. Min Act: -0.1700

Data Index: 264087 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.4885. Min Act: -0.1700

Data Index: 663004 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.4573. Min Act: -0.1700

Data Index: 1270960 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.3948. Min Act: -0.1700

Data Index: 114118 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.4260. Min Act: -0.1700

Data Index: 937052 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.4260. Min Act: -0.1700

Data Index: 227088 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.4573. Min Act: -0.1700

Data Index: 339692 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.3948. Min Act: -0.1700

Data Index: 948828 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.3948. Min Act: -0.1700

Data Index: 998009 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.3635. Min Act: -0.1700

Data Index: 19403 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.3323. Min Act: -0.1700

Data Index: 415881 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.3010. Min Act: -0.1700

Data Index: 680292 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.2385. Min Act: -0.1700

Data Index: 646508 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.2698. Min Act: -0.1700

Data Index: 675190 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.2385. Min Act: -0.1700

Data Index: 1351416 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.1448. Min Act: -0.1700

Data Index: 1197687 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.2073. Min Act: -0.1700

Data Index: 489340 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.2073. Min Act: -0.1700

Data Index: 1249642 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 7.6448. Min Range: -7.6448

Max Act: 7.1135. Min Act: -0.1700

Data Index: 739735 (C4 (Web Text))

Max Activating Token Index: 615