Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 968 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.8613. Min Act: -0.1700
Data Index: 1435882 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7988. Min Act: -0.1700
Data Index: 1611066 (Python Code)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.8301. Min Act: -0.1700
Data Index: 663200 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.8301. Min Act: -0.1700
Data Index: 1496630 (Python Code)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7988. Min Act: -0.1700
Data Index: 1522111 (Python Code)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1608319 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7988. Min Act: -0.1700
Data Index: 1507870 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1603751 (Python Code)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7676. Min Act: -0.1700
Data Index: 973102 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7363. Min Act: -0.1700
Data Index: 1454805 (Python Code)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1418153 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1530745 (Python Code)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7363. Min Act: -0.1700
Data Index: 1587023 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7676. Min Act: -0.1700
Data Index: 1446169 (Python Code)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7051. Min Act: -0.1700
Data Index: 1466677 (Python Code)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.6738. Min Act: -0.1700
Data Index: 1588622 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7051. Min Act: -0.1700
Data Index: 1606006 (Python Code)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.6738. Min Act: -0.1700
Data Index: 219355 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7363. Min Act: -0.1700
Data Index: 466500 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8613. Min Range: -4.8613
Max Act: 4.7051. Min Act: -0.1700
Data Index: 1389379 (Python Code)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19