Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 228 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.1874. Min Act: -0.1700
Data Index: 1168152 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.1086. Min Act: -0.1700
Data Index: 1359303 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0929. Min Act: -0.1700
Data Index: 997590 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0613. Min Act: -0.1700
Data Index: 793078 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0771. Min Act: -0.1700
Data Index: 472027 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0613. Min Act: -0.1700
Data Index: 604529 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0613. Min Act: -0.1700
Data Index: 378569 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0297. Min Act: -0.1700
Data Index: 923737 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0297. Min Act: -0.1700
Data Index: 136945 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0455. Min Act: -0.1700
Data Index: 1310595 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0455. Min Act: -0.1700
Data Index: 909097 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0139. Min Act: -0.1700
Data Index: 12520 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0297. Min Act: -0.1700
Data Index: 763311 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0297. Min Act: -0.1700
Data Index: 286967 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0139. Min Act: -0.1700
Data Index: 501633 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0139. Min Act: -0.1700
Data Index: 1306525 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1874. Min Range: -3.1874
Max Act: 3.0297. Min Act: -0.1700
Data Index: 557147 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1874. Min Range: -3.1874
Max Act: 2.9981. Min Act: -0.1700
Data Index: 45728 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1874. Min Range: -3.1874
Max Act: 2.9823. Min Act: -0.1700
Data Index: 1470865 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1874. Min Range: -3.1874
Max Act: 2.9823. Min Act: -0.1700
Data Index: 496601 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19