Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 60 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.4028. Min Act: -0.1700
Data Index: 1329027 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0902. Min Act: -0.1700
Data Index: 64925 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0902. Min Act: -0.1700
Data Index: 326890 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0590. Min Act: -0.1700
Data Index: 1168497 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0590. Min Act: -0.1700
Data Index: 1073919 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0590. Min Act: -0.1700
Data Index: 755574 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0277. Min Act: -0.1700
Data Index: 167837 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0590. Min Act: -0.1700
Data Index: 789514 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0590. Min Act: -0.1700
Data Index: 747651 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0277. Min Act: -0.1700
Data Index: 804073 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4028. Min Range: -4.4028
Max Act: 3.9964. Min Act: -0.1700
Data Index: 395082 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4028. Min Range: -4.4028
Max Act: 3.9964. Min Act: -0.1700
Data Index: 1313961 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0277. Min Act: -0.1700
Data Index: 95805 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0277. Min Act: -0.1700
Data Index: 456686 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4028. Min Range: -4.4028
Max Act: 4.0277. Min Act: -0.1700
Data Index: 419104 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4028. Min Range: -4.4028
Max Act: 3.9964. Min Act: -0.1700
Data Index: 642925 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4028. Min Range: -4.4028
Max Act: 3.9964. Min Act: -0.1700
Data Index: 166382 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4028. Min Range: -4.4028
Max Act: 3.9339. Min Act: -0.1700
Data Index: 145681 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4028. Min Range: -4.4028
Max Act: 3.9652. Min Act: -0.1700
Data Index: 1061814 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4028. Min Range: -4.4028
Max Act: 3.9964. Min Act: -0.1700
Data Index: 776173 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19