Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 205 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.7070. Min Act: -0.1700
Data Index: 119736 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.7070. Min Act: -0.1700
Data Index: 1290386 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6750. Min Act: -0.1700
Data Index: 711533 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6750. Min Act: -0.1700
Data Index: 1186513 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6589. Min Act: -0.1700
Data Index: 740125 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6589. Min Act: -0.1700
Data Index: 1354542 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6750. Min Act: -0.1700
Data Index: 525357 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6589. Min Act: -0.1700
Data Index: 752720 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6589. Min Act: -0.1700
Data Index: 103321 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6268. Min Act: -0.1700
Data Index: 297513 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6589. Min Act: -0.1700
Data Index: 8405 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6429. Min Act: -0.1700
Data Index: 679825 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6429. Min Act: -0.1700
Data Index: 1046316 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6429. Min Act: -0.1700
Data Index: 1150213 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6268. Min Act: -0.1700
Data Index: 1298858 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6268. Min Act: -0.1700
Data Index: 518740 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6268. Min Act: -0.1700
Data Index: 425906 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.6108. Min Act: -0.1700
Data Index: 1535937 (Python Code)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.5947. Min Act: -0.1700
Data Index: 879867 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7070. Min Range: -2.7070
Max Act: 2.5947. Min Act: -0.1700
Data Index: 37645 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19