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

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

Neuron 1321 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: 4.2846. Min Range: -4.2846

Max Act: 4.2846. Min Act: -0.1700

Data Index: 491311 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.2467. Min Act: -0.1700

Data Index: 1487372 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.2239. Min Act: -0.1700

Data Index: 889353 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1404. Min Act: -0.1700

Data Index: 106131 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1892. Min Act: -0.1700

Data Index: 1374223 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.2061. Min Act: -0.1700

Data Index: 237373 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.2329. Min Act: -0.1700

Data Index: 651797 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.2551. Min Act: -0.1700

Data Index: 804922 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1717. Min Act: -0.1700

Data Index: 1133855 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1251. Min Act: -0.1700

Data Index: 809576 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.0644. Min Act: -0.1700

Data Index: 454909 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1915. Min Act: -0.1700

Data Index: 314159 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1248. Min Act: -0.1700

Data Index: 670228 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.0969. Min Act: -0.1700

Data Index: 829800 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1466. Min Act: -0.1700

Data Index: 874361 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1749. Min Act: -0.1700

Data Index: 384161 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1624. Min Act: -0.1700

Data Index: 1172398 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1327. Min Act: -0.1700

Data Index: 597897 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1492. Min Act: -0.1700

Data Index: 347731 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 4.2846. Min Range: -4.2846

Max Act: 4.1361. Min Act: -0.1700

Data Index: 1117308 (C4 (Web Text))

Max Activating Token Index: 50