Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 90 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0384. Min Act: -0.1700
Data Index: 411496 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0068. Min Act: -0.1700
Data Index: 705232 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0384. Min Act: -0.1700
Data Index: 612402 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0226. Min Act: -0.1700
Data Index: 579115 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0384. Min Act: -0.1700
Data Index: 838228 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0226. Min Act: -0.1700
Data Index: 648077 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0226. Min Act: -0.1700
Data Index: 271321 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0068. Min Act: -0.1700
Data Index: 456298 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0068. Min Act: -0.1700
Data Index: 773593 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0384. Min Range: -3.0384
Max Act: 3.0068. Min Act: -0.1700
Data Index: 883327 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9751. Min Act: -0.1700
Data Index: 691881 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9910. Min Act: -0.1700
Data Index: 1321238 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9751. Min Act: -0.1700
Data Index: 82112 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9751. Min Act: -0.1700
Data Index: 711312 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9910. Min Act: -0.1700
Data Index: 950456 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9910. Min Act: -0.1700
Data Index: 92763 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9751. Min Act: -0.1700
Data Index: 1313528 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9593. Min Act: -0.1700
Data Index: 691526 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9751. Min Act: -0.1700
Data Index: 692330 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0384. Min Range: -3.0384
Max Act: 2.9751. Min Act: -0.1700
Data Index: 814390 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19