Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1835 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.3211. Min Act: -0.1700
Data Index: 1225262 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.2586. Min Act: -0.1700
Data Index: 784040 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.2274. Min Act: -0.1700
Data Index: 1142184 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1961. Min Act: -0.1700
Data Index: 515204 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.2274. Min Act: -0.1700
Data Index: 887126 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1336. Min Act: -0.1700
Data Index: 451412 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1336. Min Act: -0.1700
Data Index: 241888 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1961. Min Act: -0.1700
Data Index: 662585 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1336. Min Act: -0.1700
Data Index: 345573 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1336. Min Act: -0.1700
Data Index: 1070139 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1961. Min Act: -0.1700
Data Index: 947107 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1649. Min Act: -0.1700
Data Index: 1052300 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1023. Min Act: -0.1700
Data Index: 871408 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1023. Min Act: -0.1699
Data Index: 717047 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1023. Min Act: -0.1700
Data Index: 12522 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1023. Min Act: -0.1700
Data Index: 1090074 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1336. Min Act: -0.1700
Data Index: 750333 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1023. Min Act: -0.1700
Data Index: 73093 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.1336. Min Act: -0.1700
Data Index: 220763 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3211. Min Range: -4.3211
Max Act: 4.0711. Min Act: -0.1700
Data Index: 252998 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19