Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1882 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0663. Min Range: -4.0663
Max Act: 4.0663. Min Act: -0.1700
Data Index: 42308 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.8787. Min Act: -0.1700
Data Index: 849520 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.8474. Min Act: -0.1700
Data Index: 104295 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 273547 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7849. Min Act: -0.1700
Data Index: 1245373 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 441226 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 164165 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 106499 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 1285471 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 967008 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7223. Min Act: -0.1700
Data Index: 209824 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7223. Min Act: -0.1700
Data Index: 899723 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7223. Min Act: -0.1700
Data Index: 858703 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 1140824 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7223. Min Act: -0.1700
Data Index: 856214 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7536. Min Act: -0.1700
Data Index: 897489 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.6597. Min Act: -0.1700
Data Index: 58125 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.6910. Min Act: -0.1700
Data Index: 146407 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.7223. Min Act: -0.1700
Data Index: 462023 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0663. Min Range: -4.0663
Max Act: 3.6597. Min Act: -0.1700
Data Index: 810429 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19