Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2045 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6792. Min Act: -0.1700
Data Index: 1513022 (Python Code)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.7105. Min Act: -0.1700
Data Index: 1428748 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6480. Min Act: -0.1700
Data Index: 1598510 (Python Code)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6167. Min Act: -0.1700
Data Index: 1645897 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6480. Min Act: -0.1700
Data Index: 1595821 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6167. Min Act: -0.1700
Data Index: 1515783 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6167. Min Act: -0.1700
Data Index: 1654884 (Python Code)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.6167. Min Act: -0.1700
Data Index: 1575480 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5855. Min Act: -0.1700
Data Index: 1552675 (Python Code)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5855. Min Act: -0.1700
Data Index: 1572039 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5542. Min Act: -0.1700
Data Index: 1399899 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4917. Min Act: -0.1700
Data Index: 1616140 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5230. Min Act: -0.1700
Data Index: 1511745 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.5230. Min Act: -0.1700
Data Index: 1395968 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 1596632 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4917. Min Act: -0.1700
Data Index: 1428404 (Python Code)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 1411156 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 1576782 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.4605. Min Act: -0.1700
Data Index: 1650984 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7105. Min Range: -4.7105
Max Act: 4.3667. Min Act: -0.1700
Data Index: 1558571 (Python Code)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19