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

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

Neuron 1222 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: 3.7993. Min Range: -3.7993

Max Act: 3.7993. Min Act: -0.1700

Data Index: 963635 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6861. Min Act: -0.1700

Data Index: 748889 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6528. Min Act: -0.1700

Data Index: 218801 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6147. Min Act: -0.1700

Data Index: 703922 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.6123. Min Act: -0.1700

Data Index: 874602 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5594. Min Act: -0.1700

Data Index: 28033 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5346. Min Act: -0.1700

Data Index: 1311647 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5475. Min Act: -0.1700

Data Index: 454547 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5212. Min Act: -0.1700

Data Index: 1028517 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5300. Min Act: -0.1700

Data Index: 806507 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5411. Min Act: -0.1700

Data Index: 1183284 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5364. Min Act: -0.1700

Data Index: 617962 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5221. Min Act: -0.1700

Data Index: 1326145 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.5033. Min Act: -0.1700

Data Index: 853640 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.4931. Min Act: -0.1700

Data Index: 1084078 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.4846. Min Act: -0.1700

Data Index: 691489 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.4838. Min Act: -0.1700

Data Index: 632129 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.4758. Min Act: -0.1700

Data Index: 136830 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.4840. Min Act: -0.1700

Data Index: 967238 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 3.7993. Min Range: -3.7993

Max Act: 3.4613. Min Act: -0.1700

Data Index: 791322 (C4 (Web Text))

Max Activating Token Index: 154