Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1897 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0988. Min Range: -3.0988
Max Act: 3.0988. Min Act: -0.1700
Data Index: 87713 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.9250. Min Act: -0.1700
Data Index: 1592803 (Python Code)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.9250. Min Act: -0.1700
Data Index: 1544582 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.8774. Min Act: -0.1700
Data Index: 1025381 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.8456. Min Act: -0.1700
Data Index: 1470554 (Python Code)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.8297. Min Act: -0.1700
Data Index: 866267 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7979. Min Act: -0.1700
Data Index: 274942 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7979. Min Act: -0.1700
Data Index: 851322 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7819. Min Act: -0.1700
Data Index: 65005 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7660. Min Act: -0.1700
Data Index: 1207658 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7341. Min Act: -0.1700
Data Index: 1368988 (Python Code)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7341. Min Act: -0.1700
Data Index: 1380885 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7181. Min Act: -0.1700
Data Index: 1399406 (Python Code)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7021. Min Act: -0.1700
Data Index: 1042335 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7181. Min Act: -0.1700
Data Index: 619649 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7181. Min Act: -0.1700
Data Index: 792009 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.6861. Min Act: -0.1699
Data Index: 1544000 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7181. Min Act: -0.1700
Data Index: 1557236 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7181. Min Act: -0.1700
Data Index: 1386062 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0988. Min Range: -3.0988
Max Act: 2.7181. Min Act: -0.1700
Data Index: 1096696 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19