Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2031 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.6831. Min Act: -0.1700
Data Index: 1072758 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5868. Min Act: -0.1700
Data Index: 1032073 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.6029. Min Act: -0.1700
Data Index: 253430 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5707. Min Act: -0.1700
Data Index: 992508 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5707. Min Act: -0.1700
Data Index: 762860 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5707. Min Act: -0.1700
Data Index: 493358 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5384. Min Act: -0.1700
Data Index: 559649 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5384. Min Act: -0.1700
Data Index: 900219 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5061. Min Act: -0.1700
Data Index: 1228053 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5222. Min Act: -0.1700
Data Index: 1154147 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.5222. Min Act: -0.1700
Data Index: 832422 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4899. Min Act: -0.1700
Data Index: 460699 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4736. Min Act: -0.1700
Data Index: 73630 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4736. Min Act: -0.1700
Data Index: 1327560 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4899. Min Act: -0.1700
Data Index: 785021 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4736. Min Act: -0.1700
Data Index: 50341 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4736. Min Act: -0.1700
Data Index: 1247213 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4736. Min Act: -0.1700
Data Index: 521930 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4736. Min Act: -0.1700
Data Index: 669908 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6831. Min Range: -2.6831
Max Act: 2.4574. Min Act: -0.1700
Data Index: 932933 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19