Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 434 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.1302. Min Range: -5.1302
Max Act: 5.1302. Min Act: -0.1700
Data Index: 284160 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1302. Min Range: -5.1302
Max Act: 5.0364. Min Act: -0.1700
Data Index: 623559 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1302. Min Range: -5.1302
Max Act: 5.0052. Min Act: -0.1700
Data Index: 12011 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1302. Min Range: -5.1302
Max Act: 5.0052. Min Act: -0.1700
Data Index: 223493 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9739. Min Act: -0.1700
Data Index: 395102 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9739. Min Act: -0.1700
Data Index: 284493 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9427. Min Act: -0.1700
Data Index: 1189170 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8802. Min Act: -0.1700
Data Index: 1322278 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8802. Min Act: -0.1700
Data Index: 1131362 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9114. Min Act: -0.1700
Data Index: 636497 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8802. Min Act: -0.1700
Data Index: 350855 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8489. Min Act: -0.1700
Data Index: 575863 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9427. Min Act: -0.1700
Data Index: 657562 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8489. Min Act: -0.1700
Data Index: 1241461 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9427. Min Act: -0.1700
Data Index: 493626 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9114. Min Act: -0.1700
Data Index: 366228 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8802. Min Act: -0.1700
Data Index: 312682 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.9427. Min Act: -0.1700
Data Index: 547285 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8802. Min Act: -0.1700
Data Index: 927852 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1302. Min Range: -5.1302
Max Act: 4.8489. Min Act: -0.1700
Data Index: 277905 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19