Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 248 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.7044. Min Act: -0.1700
Data Index: 742231 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.4627. Min Act: -0.1700
Data Index: 132777 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.4139. Min Act: -0.1700
Data Index: 583576 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3976. Min Act: -0.1700
Data Index: 839448 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3813. Min Act: -0.1700
Data Index: 680725 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3649. Min Act: -0.1700
Data Index: 1289166 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3649. Min Act: -0.1700
Data Index: 498724 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3649. Min Act: -0.1700
Data Index: 1289148 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3649. Min Act: -0.1700
Data Index: 719460 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3158. Min Act: -0.1700
Data Index: 563825 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3322. Min Act: -0.1700
Data Index: 1606332 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3322. Min Act: -0.1700
Data Index: 105398 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3322. Min Act: -0.1700
Data Index: 776954 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3649. Min Act: -0.1700
Data Index: 629832 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3158. Min Act: -0.1700
Data Index: 613896 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3322. Min Act: -0.1700
Data Index: 1527482 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.2993. Min Act: -0.1700
Data Index: 1526772 (Python Code)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.2993. Min Act: -0.1700
Data Index: 1918 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3158. Min Act: -0.1700
Data Index: 623222 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7044. Min Range: -2.7044
Max Act: 2.3158. Min Act: -0.1700
Data Index: 400715 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19