Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1297 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.3797. Min Act: -0.1700
Data Index: 1317165 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.3142. Min Act: -0.1700
Data Index: 333737 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2813. Min Act: -0.1700
Data Index: 433464 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2813. Min Act: -0.1700
Data Index: 557625 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2483. Min Act: -0.1700
Data Index: 1291946 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2483. Min Act: -0.1700
Data Index: 101449 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2483. Min Act: -0.1700
Data Index: 589683 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2152. Min Act: -0.1700
Data Index: 1234682 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2318. Min Act: -0.1700
Data Index: 623691 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2318. Min Act: -0.1700
Data Index: 806378 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2318. Min Act: -0.1700
Data Index: 1048280 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2318. Min Act: -0.1700
Data Index: 1011490 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2318. Min Act: -0.1700
Data Index: 462473 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.2152. Min Act: -0.1700
Data Index: 791315 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.1986. Min Act: -0.1700
Data Index: 328635 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.1820. Min Act: -0.1700
Data Index: 857751 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.1820. Min Act: -0.1700
Data Index: 531966 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.1820. Min Act: -0.1700
Data Index: 680808 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.1986. Min Act: -0.1700
Data Index: 1075422 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3797. Min Range: -2.3797
Max Act: 2.1820. Min Act: -0.1700
Data Index: 90429 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19