Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 809 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.8239. Min Act: -0.1700
Data Index: 1365131 (Python Code)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.6051. Min Act: -0.1700
Data Index: 1496400 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.4801. Min Act: -0.1700
Data Index: 1413873 (Python Code)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.4176. Min Act: -0.1700
Data Index: 1461167 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.4176. Min Act: -0.1700
Data Index: 1552198 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.4489. Min Act: -0.1700
Data Index: 1392790 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3551. Min Act: -0.1700
Data Index: 1633733 (Python Code)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3864. Min Act: -0.1700
Data Index: 1424329 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3551. Min Act: -0.1700
Data Index: 1587601 (Python Code)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3551. Min Act: -0.1700
Data Index: 1438491 (Python Code)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3551. Min Act: -0.1700
Data Index: 1559386 (Python Code)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3238. Min Act: -0.1700
Data Index: 1589086 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3238. Min Act: -0.1700
Data Index: 1422067 (Python Code)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3551. Min Act: -0.1700
Data Index: 1628088 (Python Code)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3238. Min Act: -0.1700
Data Index: 1486647 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3238. Min Act: -0.1700
Data Index: 1477720 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3551. Min Act: -0.1700
Data Index: 1627141 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3238. Min Act: -0.1700
Data Index: 1443544 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.2926. Min Act: -0.1700
Data Index: 1606659 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8239. Min Range: -4.8239
Max Act: 4.3551. Min Act: -0.1700
Data Index: 1459977 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19