Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 372 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.8208. Min Act: -0.1700
Data Index: 648916 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.8048. Min Act: -0.1700
Data Index: 382512 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.8048. Min Act: -0.1700
Data Index: 47603 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.8048. Min Act: -0.1700
Data Index: 355255 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.8048. Min Act: -0.1700
Data Index: 51380 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7730. Min Act: -0.1700
Data Index: 941966 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7889. Min Act: -0.1700
Data Index: 181668 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7889. Min Act: -0.1700
Data Index: 168679 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7730. Min Act: -0.1700
Data Index: 71141 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7730. Min Act: -0.1700
Data Index: 766990 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7730. Min Act: -0.1700
Data Index: 654487 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7730. Min Act: -0.1700
Data Index: 1336686 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7889. Min Act: -0.1700
Data Index: 868521 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7570. Min Act: -0.1700
Data Index: 203080 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7411. Min Act: -0.1700
Data Index: 349232 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7251. Min Act: -0.1700
Data Index: 856774 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7251. Min Act: -0.1700
Data Index: 814714 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7251. Min Act: -0.1700
Data Index: 627015 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7411. Min Act: -0.1700
Data Index: 2651 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8208. Min Range: -2.8208
Max Act: 2.7411. Min Act: -0.1700
Data Index: 146607 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19