Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1227 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.4597. Min Act: -0.1700
Data Index: 747899 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3972. Min Act: -0.1700
Data Index: 1416936 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3660. Min Act: -0.1700
Data Index: 315066 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3660. Min Act: -0.1700
Data Index: 1650376 (Python Code)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3347. Min Act: -0.1700
Data Index: 1571309 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3347. Min Act: -0.1700
Data Index: 1315578 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3035. Min Act: -0.1700
Data Index: 47309 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3035. Min Act: -0.1700
Data Index: 1562668 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3035. Min Act: -0.1700
Data Index: 22364 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3035. Min Act: -0.1700
Data Index: 710148 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3035. Min Act: -0.1700
Data Index: 1548506 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2722. Min Act: -0.1700
Data Index: 12359 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2722. Min Act: -0.1700
Data Index: 586437 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2410. Min Act: -0.1700
Data Index: 1496340 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2722. Min Act: -0.1700
Data Index: 1612009 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.3035. Min Act: -0.1700
Data Index: 1511592 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2410. Min Act: -0.1700
Data Index: 1362361 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2410. Min Act: -0.1700
Data Index: 1485231 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2410. Min Act: -0.1700
Data Index: 68864 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4597. Min Range: -4.4597
Max Act: 4.2410. Min Act: -0.1700
Data Index: 1372258 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19