Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1860 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3864. Min Act: -0.1700
Data Index: 883692 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3864. Min Act: -0.1700
Data Index: 252791 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3864. Min Act: -0.1700
Data Index: 995120 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3701. Min Act: -0.1700
Data Index: 71791 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3537. Min Act: -0.1700
Data Index: 411932 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3537. Min Act: -0.1700
Data Index: 554607 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3374. Min Act: -0.1700
Data Index: 670028 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3537. Min Act: -0.1700
Data Index: 864353 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3374. Min Act: -0.1700
Data Index: 795659 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3374. Min Act: -0.1700
Data Index: 768948 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3374. Min Act: -0.1700
Data Index: 421874 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3374. Min Act: -0.1700
Data Index: 284396 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3210. Min Act: -0.1700
Data Index: 843036 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3210. Min Act: -0.1700
Data Index: 603490 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3045. Min Act: -0.1700
Data Index: 509643 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3045. Min Act: -0.1700
Data Index: 1557338 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3045. Min Act: -0.1700
Data Index: 571264 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3045. Min Act: -0.1700
Data Index: 272192 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3045. Min Act: -0.1700
Data Index: 16135 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3864. Min Range: -2.3864
Max Act: 2.3045. Min Act: -0.1700
Data Index: 207338 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19