Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1972 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.8392. Min Act: -0.1700
Data Index: 556825 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.8074. Min Act: -0.1700
Data Index: 707642 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7596. Min Act: -0.1700
Data Index: 407956 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7596. Min Act: -0.1700
Data Index: 928981 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7755. Min Act: -0.1700
Data Index: 669215 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7755. Min Act: -0.1700
Data Index: 1010662 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7596. Min Act: -0.1700
Data Index: 1336715 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7596. Min Act: -0.1700
Data Index: 1079857 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7276. Min Act: -0.1700
Data Index: 1592526 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7755. Min Act: -0.1700
Data Index: 1591272 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7276. Min Act: -0.1700
Data Index: 86451 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7596. Min Act: -0.1700
Data Index: 892653 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7116. Min Act: -0.1700
Data Index: 92954 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7436. Min Act: -0.1700
Data Index: 566597 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7276. Min Act: -0.1700
Data Index: 1200131 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7116. Min Act: -0.1700
Data Index: 446683 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7116. Min Act: -0.1700
Data Index: 1268642 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.6796. Min Act: -0.1700
Data Index: 1332623 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7116. Min Act: -0.1700
Data Index: 1117278 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8392. Min Range: -2.8392
Max Act: 2.7276. Min Act: -0.1700
Data Index: 832857 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19