Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 71 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0390. Min Range: -5.0390
Max Act: 5.0390. Min Act: -0.1700
Data Index: 678369 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0390. Min Range: -5.0390
Max Act: 5.0234. Min Act: -0.1700
Data Index: 19205 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.9921. Min Act: -0.1700
Data Index: 1097486 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.9296. Min Act: -0.1700
Data Index: 674553 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8827. Min Act: -0.1700
Data Index: 441935 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8984. Min Act: -0.1700
Data Index: 335735 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8515. Min Act: -0.1700
Data Index: 1123922 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8359. Min Act: -0.1700
Data Index: 981569 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8359. Min Act: -0.1700
Data Index: 282517 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8202. Min Act: -0.1700
Data Index: 230077 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8515. Min Act: -0.1700
Data Index: 914246 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8359. Min Act: -0.1700
Data Index: 1258896 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8046. Min Act: -0.1700
Data Index: 1268630 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8046. Min Act: -0.1700
Data Index: 771854 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.7890. Min Act: -0.1700
Data Index: 918397 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.8359. Min Act: -0.1700
Data Index: 90329 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.7890. Min Act: -0.1700
Data Index: 1355590 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.7734. Min Act: -0.1700
Data Index: 529305 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.7734. Min Act: -0.1700
Data Index: 280446 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0390. Min Range: -5.0390
Max Act: 4.7734. Min Act: -0.1700
Data Index: 147169 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19