Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1896 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.8731. Min Act: -0.1700
Data Index: 701071 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.8414. Min Act: -0.1700
Data Index: 200077 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.7298. Min Act: -0.1700
Data Index: 258186 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6818. Min Act: -0.1700
Data Index: 353932 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6658. Min Act: -0.1700
Data Index: 175098 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6658. Min Act: -0.1700
Data Index: 1370746 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6498. Min Act: -0.1700
Data Index: 336254 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6658. Min Act: -0.1700
Data Index: 228782 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6818. Min Act: -0.1700
Data Index: 759723 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6337. Min Act: -0.1700
Data Index: 12932 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6498. Min Act: -0.1700
Data Index: 1655597 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6498. Min Act: -0.1700
Data Index: 264495 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6498. Min Act: -0.1700
Data Index: 615985 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6337. Min Act: -0.1700
Data Index: 701271 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6498. Min Act: -0.1700
Data Index: 1189289 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6176. Min Act: -0.1700
Data Index: 413221 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6176. Min Act: -0.1700
Data Index: 695378 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6176. Min Act: -0.1700
Data Index: 664940 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6337. Min Act: -0.1700
Data Index: 136674 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8731. Min Range: -2.8731
Max Act: 2.6337. Min Act: -0.1700
Data Index: 654543 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19