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

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

Neuron 1544 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: 3.1430. Min Range: -3.1430

Max Act: 3.1430. Min Act: -0.1700

Data Index: 98099 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.1342. Min Act: -0.1700

Data Index: 858253 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0368. Min Act: -0.1700

Data Index: 300330 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0182. Min Act: -0.1700

Data Index: 897857 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0159. Min Act: -0.1700

Data Index: 995598 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0235. Min Act: -0.1700

Data Index: 629367 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0034. Min Act: -0.1700

Data Index: 1067118 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0037. Min Act: -0.1700

Data Index: 897295 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 3.1430. Min Range: -3.1430

Max Act: 3.0053. Min Act: -0.1700

Data Index: 561743 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9917. Min Act: -0.1700

Data Index: 179746 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9710. Min Act: -0.1700

Data Index: 549641 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9808. Min Act: -0.1700

Data Index: 1209595 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9800. Min Act: -0.1700

Data Index: 1285206 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9627. Min Act: -0.1700

Data Index: 993510 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9669. Min Act: -0.1700

Data Index: 1082125 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9653. Min Act: -0.1700

Data Index: 411035 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9554. Min Act: -0.1700

Data Index: 224138 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9498. Min Act: -0.1700

Data Index: 497268 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9387. Min Act: -0.1700

Data Index: 202276 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 3.1430. Min Range: -3.1430

Max Act: 2.9332. Min Act: -0.1700

Data Index: 1135985 (C4 (Web Text))

Max Activating Token Index: 315