Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1946 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0132. Min Range: -3.0132
Max Act: 3.0132. Min Act: -0.1700
Data Index: 600892 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9816. Min Act: -0.1700
Data Index: 545776 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1434110 (Python Code)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1574765 (Python Code)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1539581 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9816. Min Act: -0.1700
Data Index: 907694 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9974. Min Act: -0.1700
Data Index: 143241 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1595838 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1397276 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1413332 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9341. Min Act: -0.1700
Data Index: 912500 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1401054 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9499. Min Act: -0.1700
Data Index: 1394283 (Python Code)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9499. Min Act: -0.1700
Data Index: 1442928 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9499. Min Act: -0.1700
Data Index: 1513693 (Python Code)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9499. Min Act: -0.1700
Data Index: 1639261 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9499. Min Act: -0.1700
Data Index: 306599 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9183. Min Act: -0.1700
Data Index: 1010619 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9024. Min Act: -0.1700
Data Index: 970925 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0132. Min Range: -3.0132
Max Act: 2.9341. Min Act: -0.1700
Data Index: 1386288 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19