Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1999 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.2423. Min Act: -0.1700
Data Index: 151041 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.2110. Min Act: -0.1700
Data Index: 978575 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.2110. Min Act: -0.1700
Data Index: 642073 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.0704. Min Act: -0.1700
Data Index: 350783 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1329. Min Act: -0.1700
Data Index: 752255 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.0547. Min Act: -0.1700
Data Index: 372670 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.0860. Min Act: -0.1700
Data Index: 616886 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1485. Min Act: -0.1700
Data Index: 253541 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1173. Min Act: -0.1700
Data Index: 1186779 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1329. Min Act: -0.1700
Data Index: 645643 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1173. Min Act: -0.1700
Data Index: 511949 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1329. Min Act: -0.1700
Data Index: 44261 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1798. Min Act: -0.1700
Data Index: 1309544 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1329. Min Act: -0.1700
Data Index: 349854 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.0391. Min Act: -0.1700
Data Index: 418482 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.0704. Min Act: -0.1700
Data Index: 775899 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.0860. Min Act: -0.1700
Data Index: 68433 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1016. Min Act: -0.1700
Data Index: 27507 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.0235. Min Act: -0.1700
Data Index: 19706 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2423. Min Range: -4.2423
Max Act: 4.1016. Min Act: -0.1700
Data Index: 312848 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19