Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 572 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.2786. Min Act: -0.1700
Data Index: 932920 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.2161. Min Act: -0.1700
Data Index: 1277593 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.1536. Min Act: -0.1700
Data Index: 340970 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.1224. Min Act: -0.1699
Data Index: 207338 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.1224. Min Act: -0.1699
Data Index: 106207 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.0911. Min Act: -0.1698
Data Index: 1291456 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.1224. Min Act: -0.1699
Data Index: 115216 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.0599. Min Act: -0.1700
Data Index: 205057 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9974. Min Act: -0.1700
Data Index: 256896 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.0286. Min Act: -0.1698
Data Index: 249769 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.0599. Min Act: -0.1700
Data Index: 254458 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2786. Min Range: -6.2786
Max Act: 6.0286. Min Act: -0.1698
Data Index: 239384 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9974. Min Act: -0.1700
Data Index: 766149 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9661. Min Act: -0.1699
Data Index: 15623 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9974. Min Act: -0.1700
Data Index: 272315 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9349. Min Act: -0.1700
Data Index: 256481 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9036. Min Act: -0.1700
Data Index: 1193717 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9349. Min Act: -0.1698
Data Index: 201345 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.9036. Min Act: -0.1694
Data Index: 208808 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2786. Min Range: -6.2786
Max Act: 5.8724. Min Act: -0.1700
Data Index: 1069282 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19