Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 66 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.9966. Min Act: -0.1700
Data Index: 1076082 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.9808. Min Act: -0.1700
Data Index: 268403 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.9016. Min Act: -0.1700
Data Index: 1215958 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.8063. Min Act: -0.1700
Data Index: 993619 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.8222. Min Act: -0.1700
Data Index: 625639 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.8063. Min Act: -0.1700
Data Index: 645463 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.8063. Min Act: -0.1700
Data Index: 358399 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7585. Min Act: -0.1700
Data Index: 1309157 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7744. Min Act: -0.1700
Data Index: 666126 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7585. Min Act: -0.1700
Data Index: 1068273 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7585. Min Act: -0.1700
Data Index: 246250 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7425. Min Act: -0.1700
Data Index: 1398682 (Python Code)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7585. Min Act: -0.1700
Data Index: 652163 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7425. Min Act: -0.1700
Data Index: 62109 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7425. Min Act: -0.1700
Data Index: 418217 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7425. Min Act: -0.1700
Data Index: 91265 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7265. Min Act: -0.1700
Data Index: 883584 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7265. Min Act: -0.1700
Data Index: 256784 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7265. Min Act: -0.1700
Data Index: 121675 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9966. Min Range: -2.9966
Max Act: 2.7105. Min Act: -0.1700
Data Index: 1165211 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19