Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1988 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.4811. Min Act: -0.1700

Data Index: 108315 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.4462. Min Act: -0.1700

Data Index: 82414 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.4509. Min Act: -0.1700

Data Index: 753009 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.4152. Min Act: -0.1700

Data Index: 1263723 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.4009. Min Act: -0.1700

Data Index: 930707 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.4113. Min Act: -0.1700

Data Index: 385152 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3696. Min Act: -0.1700

Data Index: 1331689 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3612. Min Act: -0.1700

Data Index: 376998 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3659. Min Act: -0.1700

Data Index: 403564 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3393. Min Act: -0.1700

Data Index: 872190 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3428. Min Act: -0.1700

Data Index: 720474 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3590. Min Act: -0.1700

Data Index: 805372 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3352. Min Act: -0.1700

Data Index: 1211703 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3355. Min Act: -0.1700

Data Index: 1050331 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3325. Min Act: -0.1700

Data Index: 1049438 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3735. Min Act: -0.1700

Data Index: 1279502 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3133. Min Act: -0.1700

Data Index: 942394 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3201. Min Act: -0.1700

Data Index: 642085 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3458. Min Act: -0.1700

Data Index: 600509 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 3.4811. Min Range: -3.4811

Max Act: 3.3219. Min Act: -0.1700

Data Index: 94092 (C4 (Web Text))

Max Activating Token Index: 826