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

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

Neuron 581 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: 4.2676. Min Range: -4.2676

Max Act: 4.2676. Min Act: -0.1700

Data Index: 108070 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9947. Min Act: -0.1700

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9993. Min Act: -0.1700

Data Index: 1203848 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9742. Min Act: -0.1700

Data Index: 1265616 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9808. Min Act: -0.1700

Data Index: 134814 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9428. Min Act: -0.1700

Data Index: 219569 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9239. Min Act: -0.1700

Data Index: 296309 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9113. Min Act: -0.1700

Data Index: 1183704 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.9115. Min Act: -0.1700

Data Index: 802387 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8938. Min Act: -0.1700

Data Index: 472925 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8974. Min Act: -0.1700

Data Index: 448513 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8710. Min Act: -0.1700

Data Index: 836888 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8775. Min Act: -0.1700

Data Index: 491523 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8764. Min Act: -0.1700

Data Index: 850843 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8637. Min Act: -0.1700

Data Index: 730162 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8918. Min Act: -0.1700

Data Index: 64541 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8661. Min Act: -0.1700

Data Index: 1258099 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8630. Min Act: -0.1700

Data Index: 231066 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8369. Min Act: -0.1700

Data Index: 1149355 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 4.2676. Min Range: -4.2676

Max Act: 3.8409. Min Act: -0.1700

Data Index: 1033119 (C4 (Web Text))

Max Activating Token Index: 903