Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 653 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1139. Min Range: -5.1139
Max Act: 5.0826. Min Act: -0.1700
Data Index: 912811 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1139. Min Range: -5.1139
Max Act: 5.1139. Min Act: -0.1700
Data Index: 642889 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1139. Min Range: -5.1139
Max Act: 5.0826. Min Act: -0.1700
Data Index: 209360 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.9889. Min Act: -0.1700
Data Index: 227088 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8951. Min Act: -0.1700
Data Index: 1262788 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8951. Min Act: -0.1700
Data Index: 301594 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.9264. Min Act: -0.1700
Data Index: 702506 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.9576. Min Act: -0.1700
Data Index: 524763 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8639. Min Act: -0.1700
Data Index: 187112 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8951. Min Act: -0.1700
Data Index: 173132 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8951. Min Act: -0.1700
Data Index: 213630 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.9264. Min Act: -0.1700
Data Index: 994372 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.9264. Min Act: -0.1700
Data Index: 544283 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8639. Min Act: -0.1700
Data Index: 877319 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8326. Min Act: -0.1700
Data Index: 966712 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8639. Min Act: -0.1700
Data Index: 244449 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8639. Min Act: -0.1700
Data Index: 724536 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8639. Min Act: -0.1700
Data Index: 1020316 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8639. Min Act: -0.1700
Data Index: 629763 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1139. Min Range: -5.1139
Max Act: 4.8014. Min Act: -0.1700
Data Index: 1014062 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19