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

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

Neuron 1363 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: 3.9759. Min Range: -3.9759

Max Act: 3.9759. Min Act: -0.1700

Data Index: 484039 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.9697. Min Act: -0.1700

Data Index: 897669 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.8439. Min Act: -0.1700

Data Index: 121111 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.8109. Min Act: -0.1700

Data Index: 1272782 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.7645. Min Act: -0.1700

Data Index: 606549 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.7599. Min Act: -0.1700

Data Index: 522195 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.7492. Min Act: -0.1700

Data Index: 894763 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6956. Min Act: -0.1700

Data Index: 661384 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.7166. Min Act: -0.1700

Data Index: 1078841 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.7018. Min Act: -0.1700

Data Index: 76497 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.7091. Min Act: -0.1699

Data Index: 1011651 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6823. Min Act: -0.1700

Data Index: 1338608 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6642. Min Act: -0.1700

Data Index: 1267685 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6873. Min Act: -0.1700

Data Index: 684617 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6803. Min Act: -0.1700

Data Index: 899884 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6713. Min Act: -0.1700

Data Index: 1301696 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6659. Min Act: -0.1700

Data Index: 1323224 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6824. Min Act: -0.1700

Data Index: 889175 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6685. Min Act: -0.1700

Data Index: 243580 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 3.9759. Min Range: -3.9759

Max Act: 3.6490. Min Act: -0.1700

Data Index: 646036 (C4 (Web Text))

Max Activating Token Index: 270