Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.0286. Min Range: -5.0286
Max Act: 5.0286. Min Act: -0.1700
Data Index: 1355986 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.9974. Min Act: -0.1700
Data Index: 919364 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0286. Min Range: -5.0286
Max Act: 5.0286. Min Act: -0.1700
Data Index: 179383 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.9349. Min Act: -0.1700
Data Index: 545961 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.9036. Min Act: -0.1700
Data Index: 459927 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.8724. Min Act: -0.1700
Data Index: 580716 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.8099. Min Act: -0.1700
Data Index: 1625812 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6849. Min Act: -0.1700
Data Index: 870394 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.7161. Min Act: -0.1700
Data Index: 159550 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6849. Min Act: -0.1700
Data Index: 132286 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6536. Min Act: -0.1700
Data Index: 680984 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6849. Min Act: -0.1700
Data Index: 448657 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6536. Min Act: -0.1700
Data Index: 678363 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6536. Min Act: -0.1700
Data Index: 407791 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6536. Min Act: -0.1700
Data Index: 893065 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6224. Min Act: -0.1700
Data Index: 249018 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.5911. Min Act: -0.1700
Data Index: 1202106 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6224. Min Act: -0.1700
Data Index: 4382 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.5911. Min Act: -0.1700
Data Index: 360803 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0286. Min Range: -5.0286
Max Act: 4.6224. Min Act: -0.1700
Data Index: 740587 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19