Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2043 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.5573. Min Act: -0.1699
Data Index: 703483 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.5223. Min Act: -0.1695
Data Index: 624570 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.5135. Min Act: -0.1700
Data Index: 1621631 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.5135. Min Act: -0.1700
Data Index: 1428264 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.5135. Min Act: -0.1696
Data Index: 1641840 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.5047. Min Act: -0.1700
Data Index: 1292860 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.5047. Min Act: -0.1700
Data Index: 339216 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4696. Min Act: -0.1700
Data Index: 1066456 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4696. Min Act: -0.1685
Data Index: 1543607 (Python Code)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4520. Min Act: -0.1695
Data Index: 957862 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4520. Min Act: -0.1695
Data Index: 1426168 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4520. Min Act: -0.1700
Data Index: 967854 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4608. Min Act: -0.1700
Data Index: 587922 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4520. Min Act: -0.1700
Data Index: 1150380 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4520. Min Act: -0.1700
Data Index: 1337545 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4432. Min Act: -0.1700
Data Index: 405012 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4520. Min Act: -0.1692
Data Index: 1560848 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4432. Min Act: -0.1700
Data Index: 684163 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4520. Min Act: -0.1700
Data Index: 674723 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5573. Min Range: -1.5573
Max Act: 1.4432. Min Act: -0.1686
Data Index: 179018 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19