Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1817 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.8725. Min Act: -0.1700
Data Index: 639251 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.9038. Min Act: -0.1700
Data Index: 423177 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.8725. Min Act: -0.1700
Data Index: 1051628 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.8725. Min Act: -0.1700
Data Index: 284566 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7787. Min Act: -0.1700
Data Index: 1084450 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.8412. Min Act: -0.1700
Data Index: 939782 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7787. Min Act: -0.1700
Data Index: 78556 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7162. Min Act: -0.1700
Data Index: 1092528 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7475. Min Act: -0.1700
Data Index: 257542 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7162. Min Act: -0.1700
Data Index: 780321 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7162. Min Act: -0.1700
Data Index: 65598 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7787. Min Act: -0.1700
Data Index: 684097 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7162. Min Act: -0.1700
Data Index: 336254 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.6850. Min Act: -0.1700
Data Index: 749720 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.5912. Min Act: -0.1700
Data Index: 416281 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.6850. Min Act: -0.1700
Data Index: 916786 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7162. Min Act: -0.1700
Data Index: 701924 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.7162. Min Act: -0.1700
Data Index: 941009 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.6850. Min Act: -0.1700
Data Index: 360199 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9038. Min Range: -4.9038
Max Act: 4.6537. Min Act: -0.1700
Data Index: 260403 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19