Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 154 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.4208. Min Act: -0.1700
Data Index: 79392 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.4045. Min Act: -0.1700
Data Index: 1145956 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.3882. Min Act: -0.1700
Data Index: 307483 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.4045. Min Act: -0.1700
Data Index: 436645 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2899. Min Act: -0.1700
Data Index: 787654 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2899. Min Act: -0.1700
Data Index: 1007989 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2899. Min Act: -0.1700
Data Index: 122098 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2899. Min Act: -0.1700
Data Index: 934167 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2734. Min Act: -0.1700
Data Index: 605604 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2734. Min Act: -0.1700
Data Index: 709365 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2734. Min Act: -0.1700
Data Index: 771927 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2734. Min Act: -0.1700
Data Index: 147631 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2899. Min Act: -0.1700
Data Index: 816214 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2569. Min Act: -0.1700
Data Index: 1311149 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2569. Min Act: -0.1700
Data Index: 945950 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2569. Min Act: -0.1700
Data Index: 955323 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2569. Min Act: -0.1700
Data Index: 954855 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2569. Min Act: -0.1700
Data Index: 355114 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2404. Min Act: -0.1700
Data Index: 173640 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4208. Min Range: -2.4208
Max Act: 2.2404. Min Act: -0.1700
Data Index: 774000 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19