Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1906 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3913. Min Act: -0.1700
Data Index: 1077656 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3913. Min Act: -0.1700
Data Index: 547430 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3750. Min Act: -0.1700
Data Index: 856619 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3750. Min Act: -0.1700
Data Index: 711251 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3587. Min Act: -0.1700
Data Index: 791765 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3587. Min Act: -0.1700
Data Index: 81022 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3423. Min Act: -0.1700
Data Index: 49071 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3259. Min Act: -0.1700
Data Index: 273144 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2930. Min Act: -0.1700
Data Index: 1111045 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.3095. Min Act: -0.1700
Data Index: 1142368 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2930. Min Act: -0.1700
Data Index: 744687 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2766. Min Act: -0.1700
Data Index: 89391 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2766. Min Act: -0.1700
Data Index: 1342553 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2766. Min Act: -0.1700
Data Index: 1218603 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2601. Min Act: -0.1700
Data Index: 712063 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2601. Min Act: -0.1700
Data Index: 377293 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2436. Min Act: -0.1700
Data Index: 1141233 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2436. Min Act: -0.1700
Data Index: 822232 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2436. Min Act: -0.1700
Data Index: 671985 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3913. Min Range: -2.3913
Max Act: 2.2436. Min Act: -0.1700
Data Index: 110930 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19