Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 823 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.7308. Min Act: -0.1700
Data Index: 128602 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.6683. Min Act: -0.1700
Data Index: 387643 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.6995. Min Act: -0.1700
Data Index: 1254533 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.6995. Min Act: -0.1700
Data Index: 874385 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.6683. Min Act: -0.1700
Data Index: 1019958 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.6370. Min Act: -0.1700
Data Index: 1350203 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.6058. Min Act: -0.1700
Data Index: 684353 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5745. Min Act: -0.1700
Data Index: 319376 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5432. Min Act: -0.1700
Data Index: 500672 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5745. Min Act: -0.1700
Data Index: 673910 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5745. Min Act: -0.1700
Data Index: 148772 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5432. Min Act: -0.1700
Data Index: 644502 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5745. Min Act: -0.1700
Data Index: 305434 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.6370. Min Act: -0.1700
Data Index: 1137473 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5745. Min Act: -0.1700
Data Index: 958851 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5745. Min Act: -0.1700
Data Index: 325940 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5120. Min Act: -0.1700
Data Index: 1133883 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5432. Min Act: -0.1700
Data Index: 955654 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5120. Min Act: -0.1700
Data Index: 53671 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7308. Min Range: -4.7308
Max Act: 4.5432. Min Act: -0.1700
Data Index: 1014561 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19