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

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

Neuron 1051 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: 3.1936. Min Range: -3.1936

Max Act: 3.1936. Min Act: -0.1700

Data Index: 628433 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.1435. Min Act: -0.1700

Data Index: 406652 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.1507. Min Act: -0.1700

Data Index: 1273644 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.1203. Min Act: -0.1700

Data Index: 835411 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0745. Min Act: -0.1700

Data Index: 699129 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0627. Min Act: -0.1700

Data Index: 1047998 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0811. Min Act: -0.1700

Data Index: 634988 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0738. Min Act: -0.1700

Data Index: 805586 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0515. Min Act: -0.1700

Data Index: 948053 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0557. Min Act: -0.1700

Data Index: 368174 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0335. Min Act: -0.1700

Data Index: 865900 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0354. Min Act: -0.1700

Data Index: 1162568 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0320. Min Act: -0.1700

Data Index: 1232335 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0327. Min Act: -0.1700

Data Index: 318062 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0261. Min Act: -0.1700

Data Index: 569879 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0350. Min Act: -0.1700

Data Index: 599659 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0132. Min Act: -0.1700

Data Index: 322963 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0018. Min Act: -0.1699

Data Index: 1159952 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0025. Min Act: -0.1700

Data Index: 769828 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 3.1936. Min Range: -3.1936

Max Act: 3.0284. Min Act: -0.1700

Data Index: 1228735 (C4 (Web Text))

Max Activating Token Index: 207