Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1012 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.2701. Min Act: -0.1700
Data Index: 246178 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.2389. Min Act: -0.1700
Data Index: 289524 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1451. Min Act: -0.1700
Data Index: 721254 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.2389. Min Act: -0.1700
Data Index: 1334666 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1764. Min Act: -0.1700
Data Index: 162951 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1451. Min Act: -0.1700
Data Index: 1061659 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1451. Min Act: -0.1700
Data Index: 572851 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1451. Min Act: -0.1700
Data Index: 552633 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1139. Min Act: -0.1700
Data Index: 1320592 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.0826. Min Act: -0.1700
Data Index: 1126577 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.0826. Min Act: -0.1700
Data Index: 683502 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1139. Min Act: -0.1700
Data Index: 165900 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1139. Min Act: -0.1700
Data Index: 798374 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1139. Min Act: -0.1700
Data Index: 583934 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1451. Min Act: -0.1700
Data Index: 1266167 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.0826. Min Act: -0.1700
Data Index: 30105 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.1139. Min Act: -0.1700
Data Index: 527583 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.0513. Min Act: -0.1700
Data Index: 614911 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.0826. Min Act: -0.1700
Data Index: 1104540 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2701. Min Range: -4.2701
Max Act: 4.0826. Min Act: -0.1700
Data Index: 240564 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19