Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1618 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.3116. Min Act: -0.1700
Data Index: 1260542 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.3116. Min Act: -0.1700
Data Index: 1354516 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.2803. Min Act: -0.1700
Data Index: 523325 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.2491. Min Act: -0.1700
Data Index: 1168470 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.1866. Min Act: -0.1700
Data Index: 413911 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.1866. Min Act: -0.1700
Data Index: 48342 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.1553. Min Act: -0.1700
Data Index: 486872 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 397836 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.1241. Min Act: -0.1700
Data Index: 646718 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 678115 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 321365 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 694800 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0615. Min Act: -0.1700
Data Index: 1188768 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 1186204 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0615. Min Act: -0.1700
Data Index: 195327 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 698806 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0928. Min Act: -0.1700
Data Index: 205611 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0615. Min Act: -0.1700
Data Index: 1283880 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0615. Min Act: -0.1700
Data Index: 215231 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3116. Min Range: -4.3116
Max Act: 4.0615. Min Act: -0.1700
Data Index: 1183182 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19