Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 912 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0979. Min Range: -3.0979
Max Act: 3.0979. Min Act: -0.1700
Data Index: 792082 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0979. Min Range: -3.0979
Max Act: 3.0822. Min Act: -0.1700
Data Index: 131582 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0979. Min Range: -3.0979
Max Act: 3.0032. Min Act: -0.1700
Data Index: 927635 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0979. Min Range: -3.0979
Max Act: 3.0032. Min Act: -0.1700
Data Index: 962516 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9716. Min Act: -0.1700
Data Index: 262341 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9874. Min Act: -0.1700
Data Index: 545708 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9716. Min Act: -0.1700
Data Index: 371176 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9241. Min Act: -0.1700
Data Index: 207839 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9399. Min Act: -0.1700
Data Index: 732089 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9241. Min Act: -0.1700
Data Index: 472620 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9241. Min Act: -0.1700
Data Index: 1308016 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.8924. Min Act: -0.1700
Data Index: 696984 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9082. Min Act: -0.1700
Data Index: 424615 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9082. Min Act: -0.1700
Data Index: 727378 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.9082. Min Act: -0.1700
Data Index: 788617 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.8924. Min Act: -0.1700
Data Index: 1199110 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.8924. Min Act: -0.1700
Data Index: 225485 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.8924. Min Act: -0.1700
Data Index: 767156 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.8924. Min Act: -0.1700
Data Index: 758928 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0979. Min Range: -3.0979
Max Act: 2.8765. Min Act: -0.1700
Data Index: 1377925 (Python Code)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19