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

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

Neuron 741 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: 5.0884. Min Range: -5.0884

Max Act: 5.0884. Min Act: -0.1700

Data Index: 1285280 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.7134. Min Act: -0.1700

Data Index: 1208829 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.6352. Min Act: -0.1700

Data Index: 235287 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.6352. Min Act: -0.1700

Data Index: 1104835 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.5571. Min Act: -0.1700

Data Index: 1090103 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.6040. Min Act: -0.1700

Data Index: 325281 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.5571. Min Act: -0.1700

Data Index: 516152 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.5102. Min Act: -0.1700

Data Index: 502176 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4790. Min Act: -0.1700

Data Index: 1201979 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.5102. Min Act: -0.1700

Data Index: 250986 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.5415. Min Act: -0.1700

Data Index: 923139 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.5102. Min Act: -0.1700

Data Index: 291886 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.5102. Min Act: -0.1700

Data Index: 97470 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4790. Min Act: -0.1700

Data Index: 46744 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4634. Min Act: -0.1700

Data Index: 1219655 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4790. Min Act: -0.1700

Data Index: 906167 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4946. Min Act: -0.1700

Data Index: 851248 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4477. Min Act: -0.1700

Data Index: 1203150 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4477. Min Act: -0.1700

Data Index: 53647 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 5.0884. Min Range: -5.0884

Max Act: 4.4321. Min Act: -0.1700

Data Index: 970721 (C4 (Web Text))

Max Activating Token Index: 147