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

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

Neuron 1301 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.6818. Min Act: -0.1700

Data Index: 1468582 (Python Code)

Max Activating Token Index: 429

Text #1

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1354352 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.6192. Min Act: -0.1700

Data Index: 554364 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.5565. Min Act: -0.1700

Data Index: 205598 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.5565. Min Act: -0.1700

Data Index: 807705 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.5252. Min Act: -0.1700

Data Index: 691187 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.5096. Min Act: -0.1700

Data Index: 168181 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.5252. Min Act: -0.1700

Data Index: 346238 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.5096. Min Act: -0.1700

Data Index: 236956 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.5096. Min Act: -0.1700

Data Index: 1069286 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4939. Min Act: -0.1700

Data Index: 887580 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4939. Min Act: -0.1700

Data Index: 968292 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4469. Min Act: -0.1700

Data Index: 633722 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4312. Min Act: -0.1700

Data Index: 1157418 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4469. Min Act: -0.1700

Data Index: 901726 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4155. Min Act: -0.1700

Data Index: 207730 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4155. Min Act: -0.1700

Data Index: 354303 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4312. Min Act: -0.1700

Data Index: 240266 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.4469. Min Act: -0.1700

Data Index: 852180 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.7131. Min Range: -3.7131

Max Act: 3.3998. Min Act: -0.1700

Data Index: 1113272 (C4 (Web Text))

Max Activating Token Index: 669