Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2047 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.8913. Min Act: -0.1700
Data Index: 367022 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.8277. Min Act: -0.1700
Data Index: 1024424 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.8277. Min Act: -0.1700
Data Index: 995048 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.8118. Min Act: -0.1700
Data Index: 417975 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.8277. Min Act: -0.1700
Data Index: 234680 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7799. Min Act: -0.1700
Data Index: 679846 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7799. Min Act: -0.1700
Data Index: 545004 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7480. Min Act: -0.1700
Data Index: 817040 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7480. Min Act: -0.1700
Data Index: 301006 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7161. Min Act: -0.1700
Data Index: 401344 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7161. Min Act: -0.1700
Data Index: 152483 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7640. Min Act: -0.1700
Data Index: 240150 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7161. Min Act: -0.1700
Data Index: 1258308 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7001. Min Act: -0.1700
Data Index: 151996 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7321. Min Act: -0.1700
Data Index: 673510 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7001. Min Act: -0.1700
Data Index: 883761 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.6520. Min Act: -0.1700
Data Index: 25599 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7001. Min Act: -0.1700
Data Index: 953740 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.6841. Min Act: -0.1700
Data Index: 750755 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8913. Min Range: -2.8913
Max Act: 2.7001. Min Act: -0.1700
Data Index: 773601 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19