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

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

Neuron 1095 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: 5.4113. Min Range: -5.4113

Max Act: 5.4113. Min Act: -0.1700

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.2238. Min Act: -0.1700

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.2551. Min Act: -0.1700

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 1203920 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.1301. Min Act: -0.1700

Data Index: 1297753 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.1613. Min Act: -0.1700

Data Index: 682794 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.1301. Min Act: -0.1700

Data Index: 72827 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 1229186 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.0050. Min Act: -0.1700

Data Index: 44923 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 339884 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.0363. Min Act: -0.1700

Data Index: 1255389 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.0050. Min Act: -0.1700

Data Index: 1055515 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 5.4113. Min Range: -5.4113

Max Act: 5.0050. Min Act: -0.1700

Data Index: 368457 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 5.4113. Min Range: -5.4113

Max Act: 4.9113. Min Act: -0.1700

Data Index: 869237 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 5.4113. Min Range: -5.4113

Max Act: 4.9738. Min Act: -0.1700

Data Index: 341812 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 5.4113. Min Range: -5.4113

Max Act: 4.9425. Min Act: -0.1700

Data Index: 946172 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 5.4113. Min Range: -5.4113

Max Act: 4.9425. Min Act: -0.1700

Data Index: 759532 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 5.4113. Min Range: -5.4113

Max Act: 4.8488. Min Act: -0.1700

Data Index: 1290373 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 5.4113. Min Range: -5.4113

Max Act: 4.9425. Min Act: -0.1700

Data Index: 522285 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 5.4113. Min Range: -5.4113

Max Act: 4.7863. Min Act: -0.1700

Data Index: 64433 (C4 (Web Text))

Max Activating Token Index: 854