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

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

Neuron 467 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: 5.1183. Min Range: -5.1183

Max Act: 5.1183. Min Act: -0.1700

Data Index: 392844 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8683. Min Act: -0.1700

Data Index: 431344 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8683. Min Act: -0.1700

Data Index: 513090 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8058. Min Act: -0.1700

Data Index: 442231 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7433. Min Act: -0.1700

Data Index: 546547 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.8058. Min Act: -0.1700

Data Index: 1150558 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7121. Min Act: -0.1700

Data Index: 244489 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7433. Min Act: -0.1700

Data Index: 1053982 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7433. Min Act: -0.1700

Data Index: 106412 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7433. Min Act: -0.1700

Data Index: 147189 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7433. Min Act: -0.1700

Data Index: 337752 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.7433. Min Act: -0.1700

Data Index: 479182 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6496. Min Act: -0.1700

Data Index: 623121 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6496. Min Act: -0.1700

Data Index: 177335 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6496. Min Act: -0.1700

Data Index: 853629 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6496. Min Act: -0.1700

Data Index: 11421 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6183. Min Act: -0.1700

Data Index: 165627 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6496. Min Act: -0.1700

Data Index: 124867 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6183. Min Act: -0.1700

Data Index: 343570 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 5.1183. Min Range: -5.1183

Max Act: 4.6183. Min Act: -0.1700

Data Index: 398378 (C4 (Web Text))

Max Activating Token Index: 283