Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1846 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.3359. Min Act: -0.1700
Data Index: 396761 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.2574. Min Act: -0.1700
Data Index: 1327151 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.2416. Min Act: -0.1700
Data Index: 74953 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.2259. Min Act: -0.1700
Data Index: 349323 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.2259. Min Act: -0.1700
Data Index: 1347898 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.2259. Min Act: -0.1700
Data Index: 366039 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.2102. Min Act: -0.1700
Data Index: 20485 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1945. Min Act: -0.1700
Data Index: 900404 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1787. Min Act: -0.1700
Data Index: 380669 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1630. Min Act: -0.1700
Data Index: 111531 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1787. Min Act: -0.1700
Data Index: 413656 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1787. Min Act: -0.1700
Data Index: 1122087 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1630. Min Act: -0.1700
Data Index: 960584 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1630. Min Act: -0.1700
Data Index: 558901 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1630. Min Act: -0.1700
Data Index: 703401 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1472. Min Act: -0.1700
Data Index: 969217 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1472. Min Act: -0.1700
Data Index: 321039 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1315. Min Act: -0.1700
Data Index: 1156672 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1315. Min Act: -0.1700
Data Index: 218623 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3359. Min Range: -3.3359
Max Act: 3.1000. Min Act: -0.1700
Data Index: 210045 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19