Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1458 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.9072. Min Act: -0.1700
Data Index: 145642 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.7481. Min Act: -0.1700
Data Index: 960924 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.7162. Min Act: -0.1700
Data Index: 952351 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.7321. Min Act: -0.1700
Data Index: 1340998 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 1289537 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 604307 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 472215 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 840451 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6681. Min Act: -0.1700
Data Index: 584382 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6681. Min Act: -0.1700
Data Index: 217389 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 109535 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 1292619 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 543118 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6681. Min Act: -0.1700
Data Index: 912977 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6521. Min Act: -0.1700
Data Index: 562267 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6521. Min Act: -0.1700
Data Index: 380205 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6521. Min Act: -0.1700
Data Index: 1003371 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6681. Min Act: -0.1700
Data Index: 1033638 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6842. Min Act: -0.1700
Data Index: 1050211 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9072. Min Range: -2.9072
Max Act: 2.6521. Min Act: -0.1700
Data Index: 1057196 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19