Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 778 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.7917. Min Act: -0.1700
Data Index: 678289 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.7279. Min Act: -0.1700
Data Index: 1604959 (Python Code)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6959. Min Act: -0.1700
Data Index: 418827 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.7279. Min Act: -0.1700
Data Index: 1144260 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6959. Min Act: -0.1700
Data Index: 21887 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6638. Min Act: -0.1700
Data Index: 1131436 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6638. Min Act: -0.1700
Data Index: 1479733 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6638. Min Act: -0.1700
Data Index: 131709 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6478. Min Act: -0.1700
Data Index: 694391 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6478. Min Act: -0.1700
Data Index: 306948 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6317. Min Act: -0.1700
Data Index: 432916 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6317. Min Act: -0.1700
Data Index: 315774 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6317. Min Act: -0.1700
Data Index: 956313 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6317. Min Act: -0.1700
Data Index: 386325 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6478. Min Act: -0.1700
Data Index: 1241262 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6157. Min Act: -0.1700
Data Index: 1344910 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6157. Min Act: -0.1700
Data Index: 104808 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6157. Min Act: -0.1700
Data Index: 1165467 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6157. Min Act: -0.1700
Data Index: 777938 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7917. Min Range: -2.7917
Max Act: 2.6157. Min Act: -0.1700
Data Index: 1490793 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19