Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1199 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.9864. Min Act: -0.1700
Data Index: 1545352 (Python Code)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1564626 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1397929 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.9864. Min Act: -0.1700
Data Index: 1546121 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8926. Min Act: -0.1700
Data Index: 1540679 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.9551. Min Act: -0.1700
Data Index: 1513054 (Python Code)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.9239. Min Act: -0.1700
Data Index: 1432702 (Python Code)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8926. Min Act: -0.1700
Data Index: 1577941 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8926. Min Act: -0.1700
Data Index: 1588215 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8613. Min Act: -0.1700
Data Index: 1417316 (Python Code)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8300. Min Act: -0.1700
Data Index: 1634807 (Python Code)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.7988. Min Act: -0.1700
Data Index: 1471277 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.7988. Min Act: -0.1700
Data Index: 1597004 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8300. Min Act: -0.1700
Data Index: 1447510 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8300. Min Act: -0.1700
Data Index: 1474614 (Python Code)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.7988. Min Act: -0.1700
Data Index: 1566881 (Python Code)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.7362. Min Act: -0.1700
Data Index: 1550844 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.8300. Min Act: -0.1700
Data Index: 1483837 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.7988. Min Act: -0.1700
Data Index: 1617784 (Python Code)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9864. Min Range: -3.9864
Max Act: 3.7988. Min Act: -0.1700
Data Index: 1515582 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19