Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1525 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.6822. Min Act: -0.1700
Data Index: 1098900 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.6510. Min Act: -0.1700
Data Index: 86930 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.6510. Min Act: -0.1700
Data Index: 949423 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.5260. Min Act: -0.1700
Data Index: 1224573 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.4635. Min Act: -0.1700
Data Index: 1059094 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.4322. Min Act: -0.1700
Data Index: 1334775 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.4010. Min Act: -0.1700
Data Index: 832361 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.4635. Min Act: -0.1700
Data Index: 1215915 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.4322. Min Act: -0.1700
Data Index: 476078 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.4010. Min Act: -0.1700
Data Index: 1412363 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3385. Min Act: -0.1700
Data Index: 1267574 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3697. Min Act: -0.1700
Data Index: 668814 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3385. Min Act: -0.1700
Data Index: 121422 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3385. Min Act: -0.1700
Data Index: 165244 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3385. Min Act: -0.1700
Data Index: 20325 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3385. Min Act: -0.1700
Data Index: 690528 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3697. Min Act: -0.1700
Data Index: 982374 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3697. Min Act: -0.1700
Data Index: 384008 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3385. Min Act: -0.1700
Data Index: 1093776 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6822. Min Range: -4.6822
Max Act: 4.3697. Min Act: -0.1700
Data Index: 700001 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19