Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 831 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0410. Min Act: -0.1700
Data Index: 1212215 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0722. Min Act: -0.1700
Data Index: 834636 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.1035. Min Act: -0.1700
Data Index: 1190826 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0722. Min Act: -0.1700
Data Index: 980322 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.1347. Min Act: -0.1700
Data Index: 400927 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.1035. Min Act: -0.1700
Data Index: 369509 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.1035. Min Act: -0.1700
Data Index: 442133 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.1035. Min Act: -0.1700
Data Index: 918108 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0410. Min Act: -0.1700
Data Index: 440014 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0410. Min Act: -0.1700
Data Index: 747877 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0722. Min Act: -0.1700
Data Index: 148968 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0722. Min Act: -0.1700
Data Index: 264890 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0722. Min Act: -0.1700
Data Index: 1000714 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0410. Min Act: -0.1700
Data Index: 1080542 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0722. Min Act: -0.1700
Data Index: 85396 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1347. Min Range: -6.1347
Max Act: 5.9785. Min Act: -0.1700
Data Index: 615981 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0097. Min Act: -0.1700
Data Index: 1203520 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0410. Min Act: -0.1700
Data Index: 245 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0410. Min Act: -0.1700
Data Index: 830023 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1347. Min Range: -6.1347
Max Act: 6.0410. Min Act: -0.1700
Data Index: 1218717 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19