Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 219 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6709. Min Range: -4.6709
Max Act: 4.6709. Min Act: -0.1700
Data Index: 341186 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6709. Min Range: -4.6709
Max Act: 4.1709. Min Act: -0.1700
Data Index: 336395 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6709. Min Range: -4.6709
Max Act: 4.0302. Min Act: -0.1700
Data Index: 439332 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6709. Min Range: -4.6709
Max Act: 4.0146. Min Act: -0.1700
Data Index: 475780 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.9208. Min Act: -0.1700
Data Index: 826570 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.9364. Min Act: -0.1700
Data Index: 550054 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.9051. Min Act: -0.1700
Data Index: 813759 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.7487. Min Act: -0.1700
Data Index: 184278 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.8582. Min Act: -0.1700
Data Index: 1652629 (Python Code)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.8426. Min Act: -0.1700
Data Index: 787556 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.8270. Min Act: -0.1700
Data Index: 185828 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.8270. Min Act: -0.1700
Data Index: 834657 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.7800. Min Act: -0.1700
Data Index: 669244 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.7800. Min Act: -0.1700
Data Index: 372332 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.8113. Min Act: -0.1700
Data Index: 314769 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.7957. Min Act: -0.1700
Data Index: 28121 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.7018. Min Act: -0.1700
Data Index: 542690 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.8113. Min Act: -0.1700
Data Index: 1493518 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.7487. Min Act: -0.1700
Data Index: 592798 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6709. Min Range: -4.6709
Max Act: 3.7644. Min Act: -0.1700
Data Index: 156671 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19